ALBERT

Description: Background Significant investments have been made towards the implementation of mHealth applications and eRecord systems globally. However, fragmentation of these technologies remains a big challenge, often unresolved in developing countries. In particular, evidence shows little consideration for linking mHealth applications and eRecord systems. Botswana is a typical developing country in sub-Saharan Africa that has explored mHealth applications, but the solutions are not interoperable with existing eRecord systems. This paper describes Botswana’s eRecord systems interoperability landscape and provides guidance for linking mHealth applications to eRecord systems, both for Botswana and for developing countries using Botswana as an exemplar. Methods A survey and interviews of health ICT workers and a review of the Botswana National eHealth Strategy were completed. Perceived interoperability benefits, opportunities and challenges were charted and analysed, and future guidance derived. Results Survey and interview responses showed the need for interoperable mHealth applications and eRecord systems within the health sector of Botswana and within the context of the National eHealth Strategy. However, the current Strategy does not address linking mHealth applications to eRecord systems. Across Botswana’s health sectors, global interoperability standards and Application Programming Interfaces are widely used, with some level of interoperability within, but not between, public and private facilities. Further, a mix of open source and commercial eRecord systems utilising relational database systems and similar data formats are supported. Challenges for linking mHealth applications and eRecord systems in Botswana were identified and categorised into themes which led to development of guidance to enhance the National eHealth Strategy. Conclusion Interoperability between mHealth applications and eRecord systems is needed and is feasible. Opportunities and challenges for linking mHealth applications to eRecord systems were identified, and future guidance stemming from this insight presented. Findings will aid Botswana, and other developing countries, in resolving the pervasive disconnect between mHealth applications and eRecord systems.

Description: A substring u of a string T is called a minimal unique substring (MUS) of T if u occurs exactly once in T and any proper substring of u occurs at least twice in T. In this paper, we study the problem of computing MUSs for a sliding window over a given string T. We first show how the set of MUSs can change when the window slides over T. We then present an $$O(nlog sigma ')$$ O ( n log σ ′ ) -time and O(d)-space algorithm to compute MUSs for a sliding window of size d over the input string T of length n, where $$sigma 'le d$$ σ ′ ≤ d is the maximum number of distinct characters in every window.

Description: Background To enhance teleconsultation management, demands can be classified into different patterns, and the service of each pattern demand can be improved. Methods For the effective teleconsultation classification, a novel ensemble hierarchical clustering method is proposed in this study. In the proposed method, individual clustering results are first obtained by different hierarchical clustering methods, and then ensembled by one-hot encoding, the calculation and division of cosine similarity, and network graph representation. In the built network graph about the high cosine similarity, the connected demand series can be categorized into one pattern. For verification, 43 teleconsultation demand series are used as sample data, and the efficiency and quality of teleconsultation services are respectively analyzed before and after the demand classification. Results The teleconsultation demands are classified into three categories, erratic, lumpy, and slow. Under the fixed strategies, the service analysis after demand classification reveals the deficiencies of teleconsultation services, but analysis before demand classification can’t. Conclusion The proposed ensemble hierarchical clustering method can effectively category teleconsultation demands, and the effective demand categorization can enhance teleconsultation management.

Description: Background and objectives Internet-based technologies play an increasingly important role in the management and outcome of patients with chronic kidney disease (CKD). The healthcare system is currently flooded with digital innovations and internet-based technologies as a consequence of the coronavirus disease 2019 (COVID-19) pandemic. However, information about the attitude of German CKD-patients with access to online tools towards the use of remote, internet-based interactions such as video conferencing, email, electronic medical records and apps in general and for health issues in particular, are missing. Design, setting, participants, and measurements To address the use, habits and willingness of CKD patients in handling internet-based technologies we conducted a nationwide cross-sectional questionnaire survey in adults with CKD. Results We used 380 questionnaires from adult CKD patients (47.6% on dialysis, 43.7% transplanted and 8.7% CKD before renal replacement therapy) for analysis. Of these 18.9% denied using the internet at all (nonusers). Nonusers were significantly older (74.4 years, SD 11.4) than users (54.5 years, SD 14.5, p 

Description: Background Inguinal hernia repair, gallbladder removal, and knee- and hip replacements are the most commonly performed surgical procedures, but all are subject to practice variation and variable patient-reported outcomes. Shared decision-making (SDM) has the potential to reduce surgery rates and increase patient satisfaction. This study aims to evaluate the effectiveness of an SDM strategy with online decision aids for surgical and orthopaedic practice in terms of impact on surgery rates, patient-reported outcomes, and cost-effectiveness. Methods The E-valuAID-study is designed as a multicentre, non-randomized stepped-wedge study in patients with an inguinal hernia, gallstones, knee or hip osteoarthritis in six surgical and six orthopaedic departments. The primary outcome is the surgery rate before and after implementation of the SDM strategy. Secondary outcomes are patient-reported outcomes and cost-effectiveness. Patients in the usual care cluster prior to implementation of the SDM strategy will be treated in accordance with the best available clinical evidence, physician’s knowledge and preference and the patient’s preference. The intervention consists of the implementation of the SDM strategy and provision of disease-specific online decision aids. Decision aids will be provided to the patients before the consultation in which treatment decision is made. During this consultation, treatment preferences are discussed, and the final treatment decision is confirmed. Surgery rates will be extracted from hospital files. Secondary outcomes will be evaluated using questionnaires, at baseline, 3 and 6 months. Discussion The E-valuAID-study will examine the cost-effectiveness of an SDM strategy with online decision aids in patients with an inguinal hernia, gallstones, knee or hip osteoarthritis. This study will show whether decision aids reduce operation rates while improving patient-reported outcomes. We hypothesize that the SDM strategy will lead to lower surgery rates, better patient-reported outcomes, and be cost-effective. Trial registration: The Netherlands Trial Register, Trial NL8318, registered 22 January 2020. URL: https://www.trialregister.nl/trial/8318.

Description: Background This study developed a diagnostic tool to automatically detect normal, unclear and tumor images from colonoscopy videos using artificial intelligence. Methods For the creation of training and validation sets, 47,555 images in the jpg format were extracted from colonoscopy videos for 24 patients in Korea University Anam Hospital. A gastroenterologist with the clinical experience of 15 years divided the 47,555 images into three classes of Normal (25,895), Unclear (2038) and Tumor (19,622). A single shot detector, a deep learning framework designed for object detection, was trained using the 47,255 images and validated with two sets of 300 images—each validation set included 150 images (50 normal, 50 unclear and 50 tumor cases). Half of the 47,255 images were used for building the model and the other half were used for testing the model. The learning rate of the model was 0.0001 during 250 epochs (training cycles). Results The average accuracy, precision, recall, and F1 score over the category were 0.9067, 0.9744, 0.9067 and 0.9393, respectively. These performance measures had no change with respect to the intersection-over-union threshold (0.45, 0.50, and 0.55). This finding suggests the stability of the model. Conclusion Automated detection of normal, unclear and tumor images from colonoscopy videos is possible by using a deep learning framework. This is expected to provide an invaluable decision supporting system for clinical experts.

Description: Background Diabetes is a medical and economic burden in the United States. In this study, a machine learning predictive model was developed to predict unplanned medical visits among patients with diabetes, and findings were used to design a clinical intervention in the sponsoring healthcare organization. This study presents a case study of how predictive analytics can inform clinical actions, and describes practical factors that must be incorporated in order to translate research into clinical practice. Methods Data were drawn from electronic medical records (EMRs) from a large healthcare organization in the Northern Plains region of the US, from adult (≥ 18 years old) patients with type 1 or type 2 diabetes who received care at least once during the 3-year period. A variety of machine-learning classification models were run using standard EMR variables as predictors (age, body mass index (BMI), systolic blood pressure (BP), diastolic BP, low-density lipoprotein, high-density lipoprotein (HDL), glycohemoglobin (A1C), smoking status, number of diagnoses and number of prescriptions). The best-performing model after cross-validation testing was analyzed to identify strongest predictors. Results The best-performing model was a linear-basis support vector machine, which achieved a balanced accuracy (average of sensitivity and specificity) of 65.7%. This model outperformed a conventional logistic regression by 0.4 percentage points. A sensitivity analysis identified BP and HDL as the strongest predictors, such that disrupting these variables with random noise decreased the model’s overall balanced accuracy by 1.3 and 1.4 percentage points, respectively. These recommendations, along with stakeholder engagement, behavioral economics strategies, and implementation science principles helped to inform the design of a clinical intervention targeting behavioral changes. Conclusion Our machine-learning predictive model more accurately predicted unplanned medical visits among patients with diabetes, relative to conventional models. Post-hoc analysis of the model was used for hypothesis generation, namely that HDL and BP are the strongest contributors to unplanned medical visits among patients with diabetes. These findings were translated into a clinical intervention now being piloted at the sponsoring healthcare organization. In this way, this predictive model can be used in moving from prediction to implementation and improved diabetes care management in clinical settings.

Description: Background Due to the need for informatics competencies in the field of nursing, the present study was conducted to design a psychometric instrument to determine the qualification of informatics competencies of employed nurses in educational care centers. Methods The questionnaire was made by reviewing existing scientific resources and assessment tools. Two hundred nurses were selected using simple random sampling. Structural equation modeling was used using the measurement model technique and the average variance was calculated. Linear structural relations (LISREL) software was used to test the assumptions and correlations of the model. Results Findings showed relatively good estimation in the fit of first-order measurement model. The informatics knowledge subscale with a determining rate of 0.90 had the greatest explanatory effect among the subscales and informatics skill with a determining rate of 0.67 and basic computer skill with a determining rate of 0.60 were observed. The second-order measurement model of fitness indicators showed that the three factors can well explain the multidimensional construct of informatics competency. Conclusions The designed tool can be used to develop educational strategies in relation to nursing students in the field of informatics and prepare them in the rich environment of information technology, which can be helpful in training nursing instructors.

Description: Background Questionnaires are commonly used tools in telemedicine services that can help to evaluate different aspects. Selecting the ideal questionnaire for this purpose may be challenging for researchers. This study aims to review which questionnaires are used to evaluate telemedicine services in the studies, which are most common, and what aspects of telemedicine evaluation do they capture. Methods The PubMed database was searched in August 2020 to retrieve articles. Data extracted from the final list of articles included author/year of publication, journal of publication, type of evaluation, and evaluation questionnaire. Data were analyzed using descriptive statistics. Results Fifty-three articles were included in this study. The questionnaire was used for evaluating the satisfaction (49%), usability (34%), acceptance (11.5%), and implementation (2%) of telemedicine services. Among telemedicine specific questionnaires, Telehealth Usability Questionnaire (TUQ) (19%), Telemedicine Satisfaction Questionnaire (TSQ) (13%), and Service User Technology Acceptability Questionnaire (SUTAQ) (5.5%), were respectively most frequently used in the collected articles. Other most used questionnaires generally used for evaluating the users’ satisfaction, usability, and acceptance of technology were Client Satisfaction Questionnaire (CSQ) (5.5%), Questionnaire for User Interaction Satisfaction (QUIS) (5.5%), System Usability Scale (SUS) (5.5%), Patient Satisfaction Questionnaire (PSQ) (5.5%), and Technology Acceptance Model (TAM) (3.5%) respectively. Conclusion Employing specifically designed questionnaires or designing a new questionnaire with fewer questions and more comprehensiveness in terms of the issues studied provides a better evaluation. Attention to user needs, end-user acceptance, and implementation processes, along with users' satisfaction and usability evaluation, may optimize telemedicine efforts in the future.

Description: Background Clinical Decision Support Systems (CDSSs) for Prescribing are one of the innovations designed to improve physician practice performance and patient outcomes by reducing prescription errors. This study was therefore conducted to examine the effects of various CDSSs on physician practice performance and patient outcomes. Methods This systematic review was carried out by searching PubMed, Embase, Web of Science, Scopus, and Cochrane Library from 2005 to 2019. The studies were independently reviewed by two researchers. Any discrepancies in the eligibility of the studies between the two researchers were then resolved by consulting the third researcher. In the next step, we performed a meta-analysis based on medication subgroups, CDSS-type subgroups, and outcome categories. Also, we provided the narrative style of the findings. In the meantime, we used a random-effects model to estimate the effects of CDSS on patient outcomes and physician practice performance with a 95% confidence interval. Q statistics and I2 were then used to calculate heterogeneity. Results On the basis of the inclusion criteria, 45 studies were qualified for analysis in this study. CDSS for prescription drugs/COPE has been used for various diseases such as cardiovascular diseases, hypertension, diabetes, gastrointestinal and respiratory diseases, AIDS, appendicitis, kidney disease, malaria, high blood potassium, and mental diseases. In the meantime, other cases such as concurrent prescribing of multiple medications for patients and their effects on the above-mentioned results have been analyzed. The study shows that in some cases the use of CDSS has beneficial effects on patient outcomes and physician practice performance (std diff in means = 0.084, 95% CI 0.067 to 0.102). It was also statistically significant for outcome categories such as those demonstrating better results for physician practice performance and patient outcomes or both. However, there was no significant difference between some other cases and traditional approaches. We assume that this may be due to the disease type, the quantity, and the type of CDSS criteria that affected the comparison. Overall, the results of this study show positive effects on performance for all forms of CDSSs. Conclusions Our results indicate that the positive effects of the CDSS can be due to factors such as user-friendliness, compliance with clinical guidelines, patient and physician cooperation, integration of electronic health records, CDSS, and pharmaceutical systems, consideration of the views of physicians in assessing the importance of CDSS alerts, and the real-time alerts in the prescription.

Description: Background Patients with complex health care needs may suffer adverse outcomes from fragmented and delayed care, reducing well-being and increasing health care costs. Health reform efforts, especially those in primary care, attempt to mitigate risk of adverse outcomes by better targeting resources to those most in need. However, predicting who is susceptible to adverse outcomes, such as unplanned hospitalizations, ED visits, or other potentially avoidable expenditures, can be difficult, and providing intensive levels of resources to all patients is neither wanted nor efficient. Our objective was to understand if primary care teams can predict patient risk better than standard risk scores. Methods Six primary care practices risk stratified their entire patient population over a 2-year period, and worked to mitigate risk for those at high risk through care management and coordination. Individual patient risk scores created by the practices were collected and compared to a common risk score (Hierarchical Condition Categories) in their ability to predict future expenditures, ED visits, and hospitalizations. Accuracy of predictions, sensitivity, positive predictive values (PPV), and c-statistics were calculated for each risk scoring type. Analyses were stratified by whether the practice used intuition alone, an algorithm alone, or adjudicated an algorithmic risk score. Results In all, 40,342 patients were risk stratified. Practice scores had 38.6% agreement with HCC scores on identification of high-risk patients. For the 3,381 patients with reliable outcomes data, accuracy was high (0.71–0.88) but sensitivity and PPV were low (0.16–0.40). Practice-created scores had 0.02–0.14 lower sensitivity, specificity and PPV compared to HCC in prediction of outcomes. Practices using adjudication had, on average, .16 higher sensitivity. Conclusions Practices using simple risk stratification techniques had slightly worse accuracy in predicting common outcomes than HCC, but adjudication improved prediction.

Description: Background The Ministry of Health in Saudi Arabia is expanding the country’s telemedicine services by using advanced technology in health services. In doing so, an e-health application (app), Seha, was introduced in 2018 that allows individuals to have face-to-face visual medical consultations with their doctors on their smartphones. Objective This study evaluated the effectiveness of the app in improving healthcare delivery by ensuring patient satisfaction with the care given, increasing access to care, and improving efficiency in the healthcare system. Methods A cross-sectional study design was used to assess the perceptions of users of the Seha app and non-users who continued with traditional health services. The data were collected using an online survey via Google Forms between June 2020 and September 2020. Independent t tests and chi-square (χ2) tests were conducted to answer the research questions. Results There was a significant difference between users and non-users in terms of ease of access to health services (t =  − 9.38, p 

Description: We study the parameterized complexity of the problem of counting graph homomorphisms with given partial injectivity constraints, i.e., inequalities between pairs of vertices, which subsumes counting of graph homomorphisms, subgraph counting and, more generally, counting of answers to equi-join queries with inequalities. Our main result presents an exhaustive complexity classification for the problem in fixed-parameter tractable and $$#mathsf {W[1]}$$ # W [ 1 ] -complete cases. The proof relies on the framework of linear combinations of homomorphisms as independently discovered by Chen and Mengel (PODS 16) and by Curticapean, Dell and Marx in the recent breakthrough result regarding the exact complexity of the subgraph counting problem (STOC 17). Moreover, we invoke Rota’s NBC-Theorem to obtain an explicit criterion for fixed-parameter tractability based on treewidth. The abstract classification theorem is then applied to the problem of counting locally injective graph homomorphisms from small pattern graphs to large target graphs. As a consequence, we are able to fully classify its parameterized complexity depending on the class of allowed pattern graphs.

Description: The rooted triplet distance measures the structural dissimilarity of two phylogenetic trees or phylogenetic networks by counting the number of rooted phylogenetic trees with exactly three leaf labels (called rooted triplets, or triplets for short) that occur as embedded subtrees in one, but not both, of them. Suppose that $$N_1 = (V_1, E_1)$$ N 1 = ( V 1 , E 1 ) and $$N_2 = (V_2, E_2)$$ N 2 = ( V 2 , E 2 ) are phylogenetic networks over a common leaf label set of size n, that $$N_i$$ N i has level $$k_i$$ k i and maximum in-degree $$d_i$$ d i for $$i in {1,2}$$ i ∈ { 1 , 2 } , and that the networks’ out-degrees are unbounded. Write $$N = max (|V_1|, |V_2|)$$ N = max ( | V 1 | , | V 2 | ) , $$M = max (|E_1|, |E_2|)$$ M = max ( | E 1 | , | E 2 | ) , $$k = max (k_1, k_2)$$ k = max ( k 1 , k 2 ) , and $$d = max (d_1, d_2)$$ d = max ( d 1 , d 2 ) . Previous work has shown how to compute the rooted triplet distance between $$N_1$$ N 1 and $$N_2$$ N 2 in $$mathrm {O}(n log n)$$ O ( n log n ) time in the special case $$k le 1$$ k ≤ 1 . For $$k 〉 1$$ k 〉 1 , no efficient algorithms are known; applying a classic method from 1980 by Fortune et al. in a direct way leads to a running time of $${Omega }(N^{6} n^{3})$$ Ω ( N 6 n 3 ) and the only existing non-trivial algorithm imposes restrictions on the networks’ in- and out-degrees (in particular, it does not work when non-binary vertices are allowed). In this article, we develop two new algorithms with no such restrictions. Their running times are $$mathrm {O}(N^{2} M + n^{3})$$ O ( N 2 M + n 3 ) and $$mathrm {O}(M + N k^{2} d^{2} + n^{3})$$ O ( M + N k 2 d 2 + n 3 ) , respectively. We also provide implementations of our algorithms, evaluate their performance on simulated and real datasets, and make some observations on the limitations of the current definition of the rooted triplet distance in practice. Our prototype implementations have been packaged into the first publicly available software for computing the rooted triplet distance between unrestricted networks of arbitrary levels.

Description: Background Poor balance has been cited as one of the key causal factors of falls. Timely detection of balance impairment can help identify the elderly prone to falls and also trigger early interventions to prevent them. The goal of this study was to develop a surrogate approach for assessing elderly’s functional balance based on Short Form Berg Balance Scale (SFBBS) score. Methods Data were collected from a waist-mounted tri-axial accelerometer while participants performed a timed up and go test. Clinically relevant variables were extracted from the segmented accelerometer signals for fitting SFBBS predictive models. Regularized regression together with random-shuffle-split cross-validation was used to facilitate the development of the predictive models for automatic balance estimation. Results Eighty-five community-dwelling older adults (72.12 ± 6.99 year) participated in our study. Our results demonstrated that combined clinical and sensor-based variables, together with regularized regression and cross-validation, achieved moderate-high predictive accuracy of SFBBS scores (mean MAE = 2.01 and mean RMSE = 2.55). Step length, gender, gait speed and linear acceleration variables describe the motor coordination were identified as significantly contributed variables of balance estimation. The predictive model also showed moderate-high discriminations in classifying the risk levels in the performance of three balance assessment motions in terms of AUC values of 0.72, 0.79 and 0.76 respectively. Conclusions The study presented a feasible option for quantitatively accurate, objectively measured, and unobtrusively collected functional balance assessment at the point-of-care or home environment. It also provided clinicians and elderly with stable and sensitive biomarkers for long-term monitoring of functional balance.

Description: We consider the following control problem on fair allocation of indivisible goods. Given a set I of items and a set of agents, each having strict linear preferences over the items, we ask for a minimum subset of the items whose deletion guarantees the existence of a proportional allocation in the remaining instance; we call this problem Proportionality by Item Deletion (PID). Our main result is a polynomial-time algorithm that solves PID for three agents. By contrast, we prove that PID is computationally intractable when the number of agents is unbounded, even if the number k of item deletions allowed is small—we show that the problem is $${mathsf {W}}[3]$$ W [ 3 ] -hard with respect to the parameter k. Additionally, we provide some tight lower and upper bounds on the complexity of PID when regarded as a function of |I| and k. Considering the possibilities for approximation, we prove a strong inapproximability result for PID. Finally, we also study a variant of the problem where we are given an allocation $$pi $$ π in advance as part of the input, and our aim is to delete a minimum number of items such that $$pi $$ π is proportional in the remainder; this variant turns out to be $${{mathsf {N}}}{{mathsf {P}}}$$ N P -hard for six agents, but polynomial-time solvable for two agents, and we show that it is $$mathsf {W[2]}$$ W [ 2 ] -hard when parameterized by the number k of

Description: Background The electronic health record (EHR) holds the prospect of providing more complete and timely access to clinical information for biomedical research, quality assessments, and quality improvement compared to other data sources, such as administrative claims. In this study, we sought to assess the completeness and timeliness of structured diagnoses in the EHR compared to computed diagnoses for hypertension (HTN), hyperlipidemia (HLD), and diabetes mellitus (DM). Methods We determined the amount of time for a structured diagnosis to be recorded in the EHR from when an equivalent diagnosis could be computed from other structured data elements, such as vital signs and laboratory results. We used EHR data for encounters from January 1, 2012 through February 10, 2019 from an academic health system. Diagnoses for HTN, HLD, and DM were computed for patients with at least two observations above threshold separated by at least 30 days, where the thresholds were outpatient blood pressure of ≥ 140/90 mmHg, any low-density lipoprotein ≥ 130 mg/dl, or any hemoglobin A1c ≥ 6.5%, respectively. The primary measure was the length of time between the computed diagnosis and the time at which a structured diagnosis could be identified within the EHR history or problem list. Results We found that 39.8% of those with HTN, 21.6% with HLD, and 5.2% with DM did not receive a corresponding structured diagnosis recorded in the EHR. For those who received a structured diagnosis, a mean of 389, 198, and 166 days elapsed before the patient had the corresponding diagnosis of HTN, HLD, or DM, respectively, recorded in the EHR. Conclusions We found a marked temporal delay between when a diagnosis can be computed or inferred and when an equivalent structured diagnosis is recorded within the EHR. These findings demonstrate the continued need for additional study of the EHR to avoid bias when using observational data and reinforce the need for computational approaches to identify clinical phenotypes.

Description: Background Data from clinical registries may be linked to gain additional insights into disease processes, risk factors and outcomes. Identifying information varies from full names, addresses and unique identification codes to statistical linkage keys to no direct identifying information at all. A number of databases in Australia contain the statistical linkage key 581 (SLK-581). Our aim was to investigate the ability to link data using SLK-581 between two national databases, and to compare this linkage to that achieved with direct identifiers or other non-identifying variables. Methods The Australian and New Zealand Society of Cardiothoracic Surgeons database (ANZSCTS-CSD) contains fully identified data. The Australian and New Zealand Intensive Care Society database (ANZICS-APD) contains non-identified data together with SLK-581. Identifying data is removed at participating hospitals prior to central collation and storage. We used the local hospital ANZICS-APD data at a large single tertiary centre prior to deidentification and linked this to ANZSCTS-CSD data. We compared linkage using SLK-581 to linkage using non-identifying variables (dates of admission and discharge, age and sex) and linkage using a complete set of unique identifiers. We compared the rate of match, rate of mismatch and clinical characteristics between unmatched patients using the different methods. Results There were 1283 patients eligible for matching in the ANZSCTS-CSD. 1242 were matched using unique identifiers. Using non-identifying variables 1151/1242 (92.6%) patients were matched. Using SLK-581, 1202/1242 (96.7%) patients were matched. The addition of non-identifying data to SLK-581 provided few additional patients (1211/1242, 97.5%). Patients who did not match were younger, had a higher mortality risk and more non-standard procedures vs matched patients. The differences between unmatched patients using different matching strategies were small. Conclusion All strategies provided an acceptable linkage. SLK-581 improved the linkage compared to non-identifying variables, but was not as successful as direct identifiers. SLK-581 may be used to improve linkage between national registries where identifying information is not available or cannot be released.

Description: Background Studies that examine the adoption of clinical decision support (CDS) by healthcare providers have generally lacked a theoretical underpinning. The Unified Theory of Acceptance and Use of Technology (UTAUT) model may provide such a theory-based explanation; however, it is unknown if the model can be applied to the CDS literature. Objective Our overall goal was to develop a taxonomy based on UTAUT constructs that could reliably characterize CDS interventions. Methods We used a two-step process: (1) identified randomized controlled trials meeting comparative effectiveness criteria, e.g., evaluating the impact of CDS interventions with and without specific features or implementation strategies; (2) iteratively developed and validated a taxonomy for characterizing differential CDS features or implementation strategies using three raters. Results Twenty-five studies with 48 comparison arms were identified. We applied three constructs from the UTAUT model and added motivational control to characterize CDS interventions. Inter-rater reliability was as follows for model constructs: performance expectancy (κ = 0.79), effort expectancy (κ = 0.85), social influence (κ = 0.71), and motivational control (κ = 0.87). Conclusion We found that constructs from the UTAUT model and motivational control can reliably characterize features and associated implementation strategies. Our next step is to examine the quantitative relationships between constructs and CDS adoption.

Description: Clustering is a fundamental tool for analyzing large data sets. A rich body of work has been devoted to designing data-stream algorithms for the relevant optimization problems such as k-center, k-median, and k-means. Such algorithms need to be both time and and space efficient. In this paper, we address the problem of correlation clustering in the dynamic data stream model. The stream consists of updates to the edge weights of a graph on n nodes and the goal is to find a node-partition such that the end-points of negative-weight edges are typically in different clusters whereas the end-points of positive-weight edges are typically in the same cluster. We present polynomial-time, $$O(ncdot {{,mathrm{polylog},}}n)$$ O ( n · polylog n ) -space approximation algorithms for natural problems that arise. We first develop data structures based on linear sketches that allow the “quality” of a given node-partition to be measured. We then combine these data structures with convex programming and sampling techniques to solve the relevant approximation problem. Unfortunately, the standard LP and SDP formulations are not obviously solvable in $$O(ncdot {{,mathrm{polylog},}}n)$$ O ( n · polylog n ) -space. Our work presents space-efficient algorithms for the convex programming required, as well as approaches to reduce the adaptivity of the sampling.

Description: Background We developed transformer-based deep learning models based on natural language processing for early risk assessment of Alzheimer’s disease from the picture description test. Methods The lack of large datasets poses the most important limitation for using complex models that do not require feature engineering. Transformer-based pre-trained deep language models have recently made a large leap in NLP research and application. These models are pre-trained on available large datasets to understand natural language texts appropriately, and are shown to subsequently perform well on classification tasks with small training sets. The overall classification model is a simple classifier on top of the pre-trained deep language model. Results The models are evaluated on picture description test transcripts of the Pitt corpus, which contains data of 170 AD patients with 257 interviews and 99 healthy controls with 243 interviews. The large bidirectional encoder representations from transformers (BERTLarge) embedding with logistic regression classifier achieves classification accuracy of 88.08%, which improves the state-of-the-art by 2.48%. Conclusions Using pre-trained language models can improve AD prediction. This not only solves the problem of lack of sufficiently large datasets, but also reduces the need for expert-defined features.

Description: Background Assessing the quality of healthcare data is a complex task including the selection of suitable measurement methods (MM) and adequately assessing their results. Objectives To present an interoperable data quality (DQ) assessment method that formalizes MMs based on standardized data definitions and intends to support collaborative governance of DQ-assessment knowledge, e.g. which MMs to apply and how to assess their results in different situations. Methods We describe and explain central concepts of our method using the example of its first real world application in a study on predictive biomarkers for rejection and other injuries of kidney transplants. We applied our open source tool—openCQA—that implements our method utilizing the openEHR specifications. Means to support collaborative governance of DQ-assessment knowledge are the version-control system git and openEHR clinical information models. Results Applying the method on the study’s dataset showed satisfactory practicability of the described concepts and produced useful results for DQ-assessment. Conclusions The main contribution of our work is to provide applicable concepts and a tested exemplary open source implementation for interoperable and knowledge-based DQ-assessment in healthcare that considers the need for flexible task and domain specific requirements.

Description: Background Cost control and usage regulation of medical materials (MMs) are the practical issues that the government pays close attention to. Although it is well established that there is great potential to mobilize doctors and patients in participating MMs-related clinical decisions, few interventions adopt effective measures against specific behavioral deficiencies. This study aims at developing and validating an independent consultation and feedback system (ICFS) for optimizing clinical decisions on the use of MMs for inpatients needing joint replacement surgeries. Methods Development of the research protocol is based on a problem or deficiency list derived on a trans-theoretical framework which incorporates including mainly soft systems-thinking, information asymmetry, crisis-coping, dual delegation and planned behavior. The intervention consists of two main components targeting at patients and doctors respectively. Each of the intervention ingredients is designed to tackle the doctor and patient-side problems with MMs using in joint replacement surgeries. The intervention arm receives 18 months' ICFS intervention program on the basis of the routine medical services; while the control arm, only the routine medical services. Implementation of the intervention is supported by an online platform established and maintained by the Quality Assurance Center for Medical Care in Anhui Province, a smartphone-based application program (APP) and a web-based clinical support system. Discussion The implementation of this study is expected to significantly reduce the deficiencies and moral hazards in decision-making of MMs using through the output of economic, efficient, sustainable and easy-to-promote cooperative intervention programs, thus greatly reducing medical costs and standardizing medical behaviors. Trial registration number ISRCTN10152297.

Description: Background There have been few studies describing how production EMR systems can be systematically queried to identify clinically-defined populations and limited studies utilising free-text in this process. The aim of this study is to provide a generalisable methodology for constructing clinically-defined EMR-derived patient cohorts using structured and unstructured data in EMRs. Methods Patients with possible acute coronary syndrome (ACS) were used as an exemplar. Cardiologists defined clinical criteria for patients presenting with possible ACS. These were mapped to data tables within the production EMR system creating seven inclusion criteria comprised of structured data fields (orders and investigations, procedures, scanned electrocardiogram (ECG) images, and diagnostic codes) and unstructured clinical documentation. Data were extracted from two local health districts (LHD) in Sydney, Australia. Outcome measures included examination of the relative contribution of individual inclusion criteria to the identification of eligible encounters, comparisons between inclusion criterion and evaluation of consistency of data extracts across years and LHDs. Results Among 802,742 encounters in a 5 year dataset (1/1/13–30/12/17), the presence of an ECG image (54.8% of encounters) and symptoms and keywords in clinical documentation (41.4–64.0%) were used most often to identify presentations of possible ACS. Orders and investigations (27.3%) and procedures (1.4%), were less often present for identified presentations. Relevant ICD-10/SNOMED CT codes were present for 3.7% of identified encounters. Similar trends were seen when the two LHDs were examined separately, and across years. Conclusions Clinically-defined EMR-derived cohorts combining structured and unstructured data during cohort identification is a necessary prerequisite for critical validation work required for development of real-time clinical decision support and learning health systems.

Description: Background In the intensive care unit (ICU), delirium is a common, acute, confusional state associated with high risk for short- and long-term morbidity and mortality. Machine learning (ML) has promise to address research priorities and improve delirium outcomes. However, due to clinical and billing conventions, delirium is often inconsistently or incompletely labeled in electronic health record (EHR) datasets. Here, we identify clinical actions abstracted from clinical guidelines in electronic health records (EHR) data that indicate risk of delirium among intensive care unit (ICU) patients. We develop a novel prediction model to label patients with delirium based on a large data set and assess model performance. Methods EHR data on 48,451 admissions from 2001 to 2012, available through Medical Information Mart for Intensive Care-III database (MIMIC-III), was used to identify features to develop our prediction models. Five binary ML classification models (Logistic Regression; Classification and Regression Trees; Random Forests; Naïve Bayes; and Support Vector Machines) were fit and ranked by Area Under the Curve (AUC) scores. We compared our best model with two models previously proposed in the literature for goodness of fit, precision, and through biological validation. Results Our best performing model with threshold reclassification for predicting delirium was based on a multiple logistic regression using the 31 clinical actions (AUC 0.83). Our model out performed other proposed models by biological validation on clinically meaningful, delirium-associated outcomes. Conclusions Hurdles in identifying accurate labels in large-scale datasets limit clinical applications of ML in delirium. We developed a novel labeling model for delirium in the ICU using a large, public data set. By using guideline-directed clinical actions independent from risk factors, treatments, and outcomes as model predictors, our classifier could be used as a delirium label for future clinically targeted models.

Description: Background Strabismus is a complex disease that has various treatment approaches each with its own advantages and drawbacks. In this context, shared decisions making (SDM) is a communication process with the provider sharing all the relevant treatment alternatives, all the benefits, and risks of each procedure, while the patient shares all the preferences and values regarding his/her choices. In that way, SDM is a bidirectional process that goes beyond the typical informed consent. Therefore, it is known a little of the extent to which SDM influences the satisfaction with the treatment outcome along with strabismus patients. To study this correlation, an SDM-Q-9 questionnaire was provided within surgical consultations where treatment decisions were made; the SDM-Q-9 aims to assess the relationship between the post-operative patient’s satisfaction and their SMD score. Methods The study is considered a prospective observational pilot study. Eligible patients were adult patients diagnosed with strabismus, who had multiple treatment options, were given at the right of choice without being driven into a physician’s preference. Ninety-three strabismus patients were asked to fill out the SDM-Q-9 questionnaire related to their perception of SDM during the entire period of strabismus treatment. After the treatment, patients were asked to rate their satisfaction level with the surgical outcome as excellent, good, fair, and poor. Descriptive statistics and the linear regression statistical tests (Spearman, Mann Whitney U, and Kriskal–Wallis) were used as analysis tools. Results The average age of the participants was 24, where 50.6% were women. The mean SDM-Q-9 score among patients was 32 (IQR = 3). The postoperative patient satisfaction was rated as being excellent by 16 (17.2%) patients, good by 38 (40.9%), fair by 32 (34.4%), and poor by 7 patients (7.5%). Data analysis by linear regression statistical tests showed a positive correlation between the SDM-Q-9 score and the patient satisfaction related to the surgery outcome (B = 0.005, p 

Description: Background Diabetes Mellitus (DM) has become the third chronic non-communicable disease that hits patients after tumors, cardiovascular and cerebrovascular diseases, and has become one of the major public health problems in the world. Therefore, it is of great importance to identify individuals at high risk for DM in order to establish prevention strategies for DM. Methods Aiming at the problem of high-dimensional feature space and high feature redundancy of medical data, as well as the problem of data imbalance often faced. This study explored different supervised classifiers, combined with SVM-SMOTE and two feature dimensionality reduction methods (Logistic stepwise regression and LAASO) to classify the diabetes survey sample data with unbalanced categories and complex related factors. Analysis and discussion of the classification results of 4 supervised classifiers based on 4 data processing methods. Five indicators including Accuracy, Precision, Recall, F1-Score and AUC are selected as the key indicators to evaluate the performance of the classification model. Results According to the result, Random Forest Classifier combining SVM-SMOTE resampling technology and LASSO feature screening method (Accuracy = 0.890, Precision = 0.869, Recall = 0.919, F1-Score = 0.893, AUC = 0.948) proved the best way to tell those at high risk of DM. Besides, the combined algorithm helps enhance the classification performance for prediction of high-risk people of DM. Also, age, region, heart rate, hypertension, hyperlipidemia and BMI are the top six most critical characteristic variables affecting diabetes. Conclusions The Random Forest Classifier combining with SVM-SMOTE and LASSO feature reduction method perform best in identifying high-risk people of DM from individuals. And the combined method proposed in the study would be a good tool for early screening of DM.

Description: Background A central goal among researchers and policy makers seeking to implement clinical interventions is to identify key facilitators and barriers that contribute to implementation success. Despite calls from a number of scholars, empirical insights into the complex structural and cultural predictors of why decision aids (DAs) become routinely embedded in health care settings remains limited and highly variable across implementation contexts. Methods We examined associations between “reach”, a widely used indicator (from the RE-AIM model) of implementation success, and multi-level site characteristics of nine LVAD clinics engaged over 18 months in implementation and dissemination of a decision aid for left ventricular assist device (LVAD) treatment. Based on data collected from nurse coordinators, we explored factors at the level of the organization (e.g. patient volume), patient population (e.g. health literacy; average sickness level), clinician characteristics (e.g. attitudes towards decision aid; readiness for change) and process (how the aid was administered). We generated descriptive statistics for each site and calculated zero-order correlations (Pearson’s r) between all multi-level site variables including cumulative reach at 12 months and 18 months for all sites. We used principal components analysis (PCA) to examine any latent factors governing relationships between and among all site characteristics, including reach. Results We observed strongest inclines in reach of our decision aid across the first year, with uptake fluctuating over the second year. Average reach across sites was 63% (s.d. = 19.56) at 12 months and 66% (s.d. = 19.39) at 18 months. Our PCA revealed that site characteristics positively associated with reach on two distinct dimensions, including a first dimension reflecting greater organizational infrastructure and standardization (characteristic of larger, more established clinics) and a second dimension reflecting positive attitudinal orientations, specifically, openness and capacity to give and receive decision support among coordinators and patients. Conclusions Successful implementation plans should incorporate specific efforts to promote supportive and mutually informative interactions between clinical staff members and to institute systematic and standardized protocols to enhance the availability, convenience and salience of intervention tool in routine practice. Further research is needed to understand whether “core predictors” of success vary across different intervention types.

Description: Background The coronavirus disease 2019 (COVID-19) pandemic has caused health concerns worldwide since December 2019. From the beginning of infection, patients will progress through different symptom stages, such as fever, dyspnea or even death. Identifying disease progression and predicting patient outcome at an early stage helps target treatment and resource allocation. However, there is no clear COVID-19 stage definition, and few studies have addressed characterizing COVID-19 progression, making the need for this study evident. Methods We proposed a temporal deep learning method, based on a time-aware long short-term memory (T-LSTM) neural network and used an online open dataset, including blood samples of 485 patients from Wuhan, China, to train the model. Our method can grasp the dynamic relations in irregularly sampled time series, which is ignored by existing works. Specifically, our method predicted the outcome of COVID-19 patients by considering both the biomarkers and the irregular time intervals. Then, we used the patient representations, extracted from T-LSTM units, to subtype the patient stages and describe the disease progression of COVID-19. Results Using our method, the accuracy of the outcome of prediction results was more than 90% at 12 days and 98, 95 and 93% at 3, 6, and 9 days, respectively. Most importantly, we found 4 stages of COVID-19 progression with different patient statuses and mortality risks. We ranked 40 biomarkers related to disease and gave the reference values of them for each stage. Top 5 is Lymph, LDH, hs-CRP, Indirect Bilirubin, Creatinine. Besides, we have found 3 complications - myocardial injury, liver function injury and renal function injury. Predicting which of the 4 stages the patient is currently in can help doctors better assess and cure the patient. Conclusions To combat the COVID-19 epidemic, this paper aims to help clinicians better assess and treat infected patients, provide relevant researchers with potential disease progression patterns, and enable more effective use of medical resources. Our method predicted patient outcomes with high accuracy and identified a four-stage disease progression. We hope that the obtained results and patterns will aid in fighting the disease.

Description: Background Rheumatoid arthritis (RA) is an autoimmune disorder with systemic inflammation and may be induced by oxidative stress that affects an inflamed joint. Our objectives were to examine isotypes of autoantibodies against 4-hydroxy-2-nonenal (HNE) modifications in RA and associate them with increased levels of autoantibodies in RA patients. Methods Serum samples from 155 female patients [60 with RA, 35 with osteoarthritis (OA), and 60 healthy controls (HCs)] were obtained. Four novel differential HNE-modified peptide adducts, complement factor H (CFAH)1211–1230, haptoglobin (HPT)78–108, immunoglobulin (Ig) kappa chain C region (IGKC)2–19, and prothrombin (THRB)328–345, were re-analyzed using tandem mass spectrometric (MS/MS) spectra (ProteomeXchange: PXD004546) from RA patients vs. HCs. Further, we determined serum protein levels of CFAH, HPT, IGKC and THRB, HNE-protein adducts, and autoantibodies against unmodified and HNE-modified peptides. Significant correlations and odds ratios (ORs) were calculated. Results Levels of HPT in RA patients were greatly higher than the levels in HCs. Levels of HNE-protein adducts and autoantibodies in RA patients were significantly greater than those of HCs. IgM anti-HPT78−108 HNE, IgM anti-IGKC2−19, and IgM anti-IGKC2−19 HNE may be considered as diagnostic biomarkers for RA. Importantly, elevated levels of IgM anti-HPT78−108 HNE, IgM anti-IGKC2−19, and IgG anti-THRB328−345 were positively correlated with the disease activity score in 28 joints for C-reactive protein (DAS28-CRP). Further, the ORs of RA development through IgM anti-HPT78−108 HNE (OR 5.235, p 

Description: Background Researchers developing prediction models are faced with numerous design choices that may impact model performance. One key decision is how to include patients who are lost to follow-up. In this paper we perform a large-scale empirical evaluation investigating the impact of this decision. In addition, we aim to provide guidelines for how to deal with loss to follow-up. Methods We generate a partially synthetic dataset with complete follow-up and simulate loss to follow-up based either on random selection or on selection based on comorbidity. In addition to our synthetic data study we investigate 21 real-world data prediction problems. We compare four simple strategies for developing models when using a cohort design that encounters loss to follow-up. Three strategies employ a binary classifier with data that: (1) include all patients (including those lost to follow-up), (2) exclude all patients lost to follow-up or (3) only exclude patients lost to follow-up who do not have the outcome before being lost to follow-up. The fourth strategy uses a survival model with data that include all patients. We empirically evaluate the discrimination and calibration performance. Results The partially synthetic data study results show that excluding patients who are lost to follow-up can introduce bias when loss to follow-up is common and does not occur at random. However, when loss to follow-up was completely at random, the choice of addressing it had negligible impact on model discrimination performance. Our empirical real-world data results showed that the four design choices investigated to deal with loss to follow-up resulted in comparable performance when the time-at-risk was 1-year but demonstrated differential bias when we looked into 3-year time-at-risk. Removing patients who are lost to follow-up before experiencing the outcome but keeping patients who are lost to follow-up after the outcome can bias a model and should be avoided. Conclusion Based on this study we therefore recommend (1) developing models using data that includes patients that are lost to follow-up and (2) evaluate the discrimination and calibration of models twice: on a test set including patients lost to follow-up and a test set excluding patients lost to follow-up.

Description: Following publication of the original article [1], it was reported that the contents of Additional file 2 were a duplicate of the files for Additional file 1.

Description: Background Information literacy competency is one of the requirements to implement Evidence-Based Practice (EBP) in nursing. It is necessary to pay attention to curricular development and use new educational methods such as virtual education to strengthen information literacy competency in nursing students. Given the scarcity of the studies on the effectiveness of virtual education in nursing, particularly in Iran, and the positive university atmosphere regarding the use of virtual education, this study investigated the effect of virtual education on the undergraduate nursing students’ information literacy competency for EBP. Methods This interventional study was performed with two groups of intervention and control and a pretest and posttest design. Seventy-nine nursing students were selected and assigned to the intervention or control groups by random sampling. Virtual education of the information literacy was uploaded on a website in the form of six modules delivered in four weeks. Questionnaires of demographic information and information literacy for EBP were used to collect data before and one month after the virtual education. Results The results showed no significant difference between the control and intervention groups in all dimensions of information literacy competency in the pre-test stage. In the post-test, the virtual education improved dimensions of information seeking skills (t = 3.14, p = 0.002) and knowledge about search operators (t = 39.84, p = 0.001) in the intervention groups compared with the control group. The virtual education did not have any significant effect on the use of different information resources and development of search strategy with assessing the frequency of selecting the most appropriate search statement in the intervention group. Conclusion Virtual education had a significant effect on information seeking skills and knowledge about search operators in nursing students. Nurse educators can benefit from our experiences in designing this method for the use of virtual education programs in nursing schools. Given the lack of effectiveness of this program in using different information resources and development of search strategy, nurse educators are recommended to train information literacy for EBP by integrating several approaches such as virtual (online and offline) and face-to-face education.

Description: Background U.S. hospitals and dialysis centers are penalized for 30-day hospital readmissions of dialysis patients, despite little infrastructure to facilitate care transitions between these settings. We are developing a third-party web-based information exchange platform, DialysisConnect, to enable clinicians to view and exchange information about dialysis patients during admission, hospitalization, and discharge. This health information technology solution could serve as a flexible and relatively affordable solution for dialysis facilities and hospitals across the nation who are seeking to serve as true partners in the improved care of dialysis patients. The purpose of this study was to evaluate the perceived coherence of DialysisConnect to key clinical stakeholders, to prepare messaging for implementation. Methods As part of a hybrid effectiveness-implementation study guided by Normalization Process Theory, we collected data on stakeholder perceptions of continuity of care for patients receiving maintenance dialysis and a DialysisConnect prototype before completing development and piloting the system. We conducted four focus groups with stakeholders from one academic hospital and associated dialysis centers [hospitalists (n = 5), hospital staff (social workers, nurses, pharmacists; n = 9), nephrologists (n = 7), and dialysis clinic staff (social workers, nurses; n = 10)]. Transcriptions were analyzed thematically within each component of the construct of coherence (differentiation, communal specification, individual specification, and internalization). Results Participants differentiated DialysisConnect from usual care variously as an information dashboard, a quick-exchange communication channel, and improved discharge information delivery; some could not differentiate it in terms of workflow. The purpose of DialysisConnect (communal specification) was viewed as fully coherent only for communicating outside of the same healthcare system. Current system workarounds were acknowledged as deterrents for practice change. All groups delegated DialysisConnect tasks (individual specification) to personnel besides themselves. Partial internalization of DialysisConnect was achieved only by dialysis clinic staff, based on experience with similar technology. Conclusions Implementing DialysisConnect for clinical users in both settings will require presenting a composite picture of current communication processes from all stakeholder groups to correct single-group misunderstandings, as well as providing data about care transitions communication beyond the local context to ease resistance to practice change.

Description: Background Researchers and policy makers have long suspected that people have differing, and potentially nefarious, motivations for participating in stated-preference studies such as discrete-choice experiments (DCE). While anecdotes and theories exist on why people participate in surveys, there is a paucity of evidence exploring variation in preferences for participating in stated-preference studies. Methods We used a DCE to estimate preferences for participating in preference research among an online survey panel sample. Preferences for the characteristics of a study to be conducted at a local hospital were assessed across five attributes (validity, relevance, bias, burden, time and payment) and described across three levels using a starring system. A D-efficient experimental design was used to construct three blocks of 12 choice tasks with two profiles each. Respondents were also asked about factors that motivated their choices. Mixed logistic regression was used to analyze the aggregate sample and latent class analysis identified segments of respondents. Results 629 respondents completed the experiment. In aggregate “study validity” was most important. Latent class results identified two segments based on underlying motivations: a quality-focused segment (76%) who focused most on validity, relevance, and bias and a convenience-focused segment (24%) who focused most on reimbursement and time. Quality-focused respondents spent more time completing the survey (p 

Description: Background This study aims to explore the information chain management model of large instrument and equipment inter-working in the operating room (OR) led by information nurses. Methods Through the chain management process of large instruments and equipment in the OR, which was based on information nurses, the management model of inter-working and integrating information chain was established, the key links were controlled, and the whole life cycle management of instruments and equipment from expected procurement to scrapping treatment was realized. Using the cluster sampling method, 1562 surgical patients were selected. Among these patients, 749 patients were assigned to the control group before the running mode, and 813 patients were assigned to the observation group after the running mode. The related indexes for large instrument and equipment management in the department before and after the running mode were compared. Results In the observation group, the average time of equipment registration was (22.05 ± 2.36), the cost was reduced by 2220 yuan/year, and the satisfaction rate of the nursing staff was 97.62%. These were significantly better, when compared to the control group (P 

Description: Background Social networking sites such as Facebook® can contribute to health promotion and behaviour change activities, but are currently underused for this purpose. In Germany, health insurance companies are relevant public health agencies that are responsible for health promotion, primary prevention, and health education. We intended to analyse the Facebook® accounts of health insurance providers to explore the range of prevention topics addressed, identify the communication formats used, and analyse user activity stimulated by prevention-related posts. Methods We performed a quantitative content analysis of text and picture data on Facebook® accounts (9 months in retrospect) in a cross-sectional study design. 64/159 German health insurance providers hosted a Facebook® page, 25/64 posted ≥ 10 posts/months. Among those 25, we selected 17 health insurance companies (12 public, 5 private) for analysis. All posts were categorized according to domains in the classification system that was developed for this study, and the number of likes and comments was counted. The data were analysed using descriptive statistics. Results We collected 3,763 Facebook® posts, 32% of which had a focus on prevention. The frequency of prevention-related posts varied among health insurance providers (1–25 per month). The behaviours addressed most frequently were healthy nutrition, physical activity, and stress/anxiety relief, often in combination with each other. All these topics yielded a moderate user engagement (30–120 likes, 2–10 comments per post). User engagement was highest when a competition or quiz were posted (11% of posts). The predominant communication pattern was health education, often supplemented by photos or links, or information about offline events (e.g. a public run). Some providers regularly engaged in two-side communication with users, inviting tips, stories or recipes, or responding to individual comments. Still, the interactive potential offered by Facebook® was only partly exploited. Conclusions Those few health insurace companies that regularly post content about prevention or healthy lifestyles on their Facebook® accounts comply with suggestions given for social media communication. Still, many health insurance providers fail to actively interact with wider audiences. Whether health communication on Facebook® can actually increase health literacy and lead to behaviour changes still needs to be evaluated.

Description: Background Systemic inflammatory response syndrome (SIRS) is defined as a non-specific inflammatory process in the absence of infection. SIRS increases susceptibility for organ dysfunction, and frequently affects the clinical outcome of affected patients. We evaluated a knowledge-based, interoperable clinical decision-support system (CDSS) for SIRS detection on a pediatric intensive care unit (PICU). Methods The CDSS developed retrieves routine data, previously transformed into an interoperable format, by using model-based queries and guideline- and knowledge-based rules. We evaluated the CDSS in a prospective diagnostic study from 08/2018–03/2019. 168 patients from a pediatric intensive care unit of a tertiary university hospital, aged 0 to 18 years, were assessed for SIRS by the CDSS and by physicians during clinical routine. Sensitivity and specificity (when compared to the reference standard) with 95% Wald confidence intervals (CI) were estimated on the level of patients and patient-days. Results Sensitivity and specificity was 91.7% (95% CI 85.5–95.4%) and 54.1% (95% CI 45.4–62.5%) on patient level, and 97.5% (95% CI 95.1–98.7%) and 91.5% (95% CI 89.3–93.3%) on the level of patient-days. Physicians’ SIRS recognition during clinical routine was considerably less accurate (sensitivity of 62.0% (95% CI 56.8–66.9%)/specificity of 83.3% (95% CI 80.4–85.9%)) when measurd on the level of patient-days. Evaluation revealed valuable insights for the general design of the CDSS as well as specific rule modifications. Despite a lower than expected specificity, diagnostic accuracy was higher than the one in daily routine ratings, thus, demonstrating high potentials of using our CDSS to help to detect SIRS in clinical routine. Conclusions We successfully evaluated an interoperable CDSS for SIRS detection in PICU. Our study demonstrated the general feasibility and potentials of the implemented algorithms but also some limitations. In the next step, the CDSS will be optimized to overcome these limitations and will be evaluated in a multi-center study. Trial registration: NCT03661450 (ClinicalTrials.gov); registered September 7, 2018.

Description: Background The Ministry of Health of Malaysia has invested significant resources to implement an electronic health record (EHR) system to ensure the full automation of hospitals for coordinated care delivery. Thus, evaluating whether the system has been effectively utilized is necessary, particularly regarding how it predicts the post-implementation primary care providers’ performance impact. Methods Convenience sampling was employed for data collection in three government hospitals for 7 months. A standardized effectiveness survey for EHR systems was administered to primary health care providers (specialists, medical officers, and nurses) as they participated in medical education programs. Empirical data were assessed by employing partial least squares-structural equation modeling for hypothesis testing. Results The results demonstrated that knowledge quality had the highest score for predicting performance and had a large effect size, whereas system compatibility was the most substantial system quality component. The findings indicated that EHR systems supported the clinical tasks and workflows of care providers, which increased system quality, whereas the increased quality of knowledge improved user performance. Conclusion Given these findings, knowledge quality and effective use should be incorporated into evaluating EHR system effectiveness in health institutions. Data mining features can be integrated into current systems for efficiently and systematically generating health populations and disease trend analysis, improving clinical knowledge of care providers, and increasing their productivity. The validated survey instrument can be further tested with empirical surveys in other public and private hospitals with different interoperable EHR systems.

Description: The knapsack problem is one of the classical problems in combinatorial optimization: Given a set of items, each specified by its size and profit, the goal is to find a maximum profit packing into a knapsack of bounded capacity. In the online setting, items are revealed one by one and the decision, if the current item is packed or discarded forever, must be done immediately and irrevocably upon arrival. We study the online variant in the random order model where the input sequence is a uniform random permutation of the item set. We develop a randomized (1/6.65)-competitive algorithm for this problem, outperforming the current best algorithm of competitive ratio 1/8.06 (Kesselheim et al. in SIAM J Comput 47(5):1939–1964, 2018). Our algorithm is based on two new insights: We introduce a novel algorithmic approach that employs two given algorithms, optimized for restricted item classes, sequentially on the input sequence. In addition, we study and exploit the relationship of the knapsack problem to the 2-secretary problem. The generalized assignment problem (GAP) includes, besides the knapsack problem, several important problems related to scheduling and matching. We show that in the same online setting, applying the proposed sequential approach yields a (1/6.99)-competitive randomized algorithm for GAP. Again, our proposed algorithm outperforms the current best result of competitive ratio 1/8.06 (Kesselheim et al. in SIAM J Comput 47(5):1939–1964, 2018).

Description: Background We know little about the best approaches to design training for healthcare professionals. We thus studied how user-centered and theory-based design contribute to the development of a distance learning program for professionals, to increase their shared decision-making (SDM) with older adults living with neurocognitive disorders and their caregivers. Methods In this mixed-methods study, healthcare professionals who worked in family medicine clinics and homecare services evaluated a training program in a user-centered approach with several iterative phases of quantitative and qualitative evaluation, each followed by modifications. The program comprised an e-learning activity and five evidence summaries. A subsample assessed the e-learning activity during semi-structured think-aloud sessions. A second subsample assessed the evidence summaries they received by email. All participants completed a theory-based questionnaire to assess their intention to adopt SDM. Descriptive statistical analyses and qualitative thematic analyses were integrated at each round to prioritize training improvements with regard to the determinants most likely to influence participants’ intention. Results Of 106 participants, 98 completed their evaluations of either the e-learning activity or evidence summary (93%). The professions most represented were physicians (60%) and nurses (15%). Professionals valued the e-learning component to gain knowledge on the theory and practice of SDM, and the evidence summaries to apply the knowledge gained through the e-learning activity to diverse clinical contexts. The iterative design process allowed addressing most weaknesses reported. Participants’ intentions to adopt SDM and to use the summaries were high at baseline and remained positive as the rounds progressed. Attitude and social influence significantly influenced participants' intention to use the evidence summaries (P 

Description: Background Summative eHealth evaluations frequently lack quality, which affects the generalizability of the evidence, and its use in practice and further research. To guarantee quality, a number of activities are recommended in the guidelines for evaluation planning. This study aimed to examine a case of an eHealth evaluation planning in a multi-national and interdisciplinary setting and to provide recommendations for eHealth evaluation planning guidelines. Methods An empirical eHealth evaluation process was developed through a case study. The empirical process was compared with selected guidelines for eHealth evaluation planning using a pattern-matching technique. Results Planning in the interdisciplinary and multi-national team demanded extensive negotiation and alignment to support the future use of the evidence created. The evaluation planning guidelines did not provide specific strategies for different set-ups of the evaluation teams. Further, they did not address important aspects of quality evaluation, such as feasibility analysis of the outcome measures and data collection, monitoring of data quality, and consideration of the methods and measures employed in similar evaluations. Conclusions Activities to prevent quality problems need to be incorporated in the guidelines for evaluation planning. Additionally, evaluators could benefit from guidance in evaluation planning related to the different set-ups of the evaluation teams.

Description: Background No case definition of Type 1 diabetes (T1D) for the claims data has been proposed in Japan yet. This study aimed to evaluate the performance of candidate case definitions for T1D using Electronic health care records (EHR) and claims data in a University Hospital in Japan. Methods The EHR and claims data for all the visiting patients in a University Hospital were used. As the candidate case definitions for claims data, we constructed 11 definitions by combinations of International Statistical Classification of Diseases and Related Health Problems, Tenth Revision. (ICD 10) code of T1D, the claims code of insulin needles for T1D patients, basal insulin, and syringe pump for continuous subcutaneous insulin infusion (CSII). We constructed a predictive model for T1D patients using disease names, medical practices, and medications as explanatory variables. The predictive model was applied to patients of test group (validation data), and performances of candidate case definitions were evaluated. Results As a result of performance evaluation, the sensitivity of the confirmed disease name of T1D was 32.9 (95% CI: 28.4, 37.2), and positive predictive value (PPV) was 33.3 (95% CI: 38.0, 38.4). By using the case definition of both the confirmed diagnosis of T1D and either of the claims code of the two insulin treatment methods (i.e., syringe pump for CSII and insulin needles), PPV improved to 90.2 (95% CI: 85.2, 94.4). Conclusions We have established a case definition with high PPV, and the case definition can be used for precisely detecting T1D patients from claims data in Japan.

Description: Objective To explore an effective algorithm based on artificial neural network to pick correctly the minority of pregnant women with SLE suffering fetal loss outcomes from the majority with live birth and train a well behaved model as a clinical decision assistant. Methods We integrated the thoughts of comparative and focused study into the artificial neural network and presented an effective algorithm aiming at imbalanced learning in small dataset. Results We collected 469 non-trivial pregnant patients with SLE, where 420 had live-birth outcomes and the other 49 patients ended in fetal loss. A well trained imbalanced-learning model had a high sensitivity of 19/21 ($$90.8\%$$ 90.8 % ) for the identification of patients with fetal loss outcomes. Discussion The misprediction of the two patients was explainable. Algorithm improvements in artificial neural network framework enhanced the identification in imbalanced learning problems and the external validation increased the reliability of algorithm. Conclusion The well-trained model was fully qualified to assist healthcare providers to make timely and accurate decisions.

Description: Background Semantic categorization analysis of clinical trials eligibility criteria based on natural language processing technology is crucial for the task of optimizing clinical trials design and building automated patient recruitment system. However, most of related researches focused on English eligibility criteria, and to the best of our knowledge, there are no researches studied the Chinese eligibility criteria. Thus in this study, we aimed to explore the semantic categories of Chinese eligibility criteria. Methods We downloaded the clinical trials registration files from the website of Chinese Clinical Trial Registry (ChiCTR) and extracted both the Chinese eligibility criteria and corresponding English eligibility criteria. We represented the criteria sentences based on the Unified Medical Language System semantic types and conducted the hierarchical clustering algorithm for the induction of semantic categories. Furthermore, in order to explore the classification performance of Chinese eligibility criteria with our developed semantic categories, we implemented multiple classification algorithms, include four baseline machine learning algorithms (LR, NB, kNN, SVM), three deep learning algorithms (CNN, RNN, FastText) and two pre-trained language models (BERT, ERNIE). Results We totally developed 44 types of semantic categories, summarized 8 topic groups, and investigated the average incidence and prevalence in 272 hepatocellular carcinoma related Chinese clinical trials. Compared with the previous proposed categories in English eligibility criteria, 13 novel categories are identified in Chinese eligibility criteria. The classification result shows that most of semantic categories performed quite well, the pre-trained language model ERNIE achieved best performance with macro-average F1 score of 0.7980 and micro-average F1 score of 0.8484. Conclusion As a pilot study of Chinese eligibility criteria analysis, we developed the 44 semantic categories by hierarchical clustering algorithms for the first times, and validated the classification capacity with multiple classification algorithms.

Description: Background Robust, flexible, and integrated health information (HIS) systems are essential to achieving national and international goals in health and development. Such systems are still uncommon in most low and middle income countries. This article describes a first-phase activity in Tanzania to integrate the country’s vertical health management information system with the help of an interoperability layer that enables cross-program data exchange. Methods From 2014 to 2019, the Tanzanian government and partners implemented a five-step procedure based on the “Mind the GAPS” (governance, architecture, program management, and standards) framework and using both proprietary and open-source tools. In collaboration with multiple stakeholders, the team developed the system to address major data challenges via four fully documented “use case scenarios” addressing data exchange among hospitals, between services and the supply chain, across digital data systems, and within the supply chain reporting system. This work included developing the architecture for health system data exchange, putting a middleware interoperability layer in place to facilitate the exchange, and training to support use of the system and the data it generates. Results Tanzania successfully completed the five-step procedure for all four use cases. Data exchange is currently enabled among 15 separate information systems, and has resulted in improved data availability and significant time savings. The government has adopted the health information exchange within the national strategy for health care information, and the system is being operated and managed by Tanzanian officials. Conclusion Developing an integrated HIS requires a significant time investment; but ultimately benefit both programs and patients. Tanzania’s experience may interest countries that are developing their HIS programs.

Description: Background The uptake of complex clinical decision support systems (CDSS) in daily practice remains low, despite the proven potential to reduce medical errors and to improve the quality of care. To improve successful implementation of a complex CDSS this study aims to identify the factors that hinder, or alleviate the acceptance of, clinicians toward the use of a complex CDSS for treatment allocation of patients with chronic low back pain. Methods We tested a research model in which the intention to use a CDSS by clinicians is influenced by the perceived usefulness; this usefulness, in turn is influenced by the perceived service benefits and perceived service risks. An online survey was created to test our research model and the data was analysed using Partial Least Squares Structural Equation Modelling. The study population consisted of clinicians. The online questionnaire started with demographic questions and continued with a video animation of the complex CDSS followed by the set of measurement items. The online questionnaire ended with two open questions enquiring the reasons to use and not use, a complex CDSS. Results Ninety-eight participants (46% general practitioners, 25% primary care physical therapists, and 29% clinicians at a rehabilitation centre) fully completed the questionnaire. Fifty-two percent of the respondents were male. The average age was 48 years (SD ± 12.2). The causal model suggests that perceived usefulness is the main factor contributing to the intention to use a complex CDSS. Perceived service benefits and risks are both significant antecedents of perceived usefulness and perceived service risks are affected by the perceived threat to autonomy and trusting beliefs, particularly benevolence and competence. Conclusions To improve the acceptance of complex CDSSs it is important to address the risks, but the main focus during the implementation phase should be on the expected improvements in patient outcomes and the overall gain for clinicians. Our results will help the development of complex CDSSs that fit more into the daily clinical practice of clinicians.

Description: Background This paper describes a model for estimating COVID-19 related excess deaths that are a direct consequence of insufficient hospital ward bed and intensive care unit (ICU) capacity. Methods Compartmental models were used to estimate deaths under different combinations of ICU and ward care required and received in England up to late April 2021. Model parameters were sourced from publicly available government information and organisations collating COVID-19 data. A sub-model was used to estimate the mortality scalars that represent increased mortality due to insufficient ICU or general ward bed capacity. Three illustrative scenarios for admissions numbers, ‘Optimistic’, ‘Middling’ and ‘Pessimistic’, were modelled and compared with the subsequent observations to the 3rd February. Results The key output was the demand and capacity model described. There were no excess deaths from a lack of capacity in the ‘Optimistic’ scenario. Several of the ‘Middling’ scenario applications resulted in excess deaths—up to 597 deaths (0.6% increase) with a 20% reduction compared to best estimate ICU capacity. All the ‘Pessimistic’ scenario applications resulted in excess deaths, ranging from 49,178 (17.0% increase) for a 20% increase in ward bed availability, to 103,735 (35.8% increase) for a 20% shortfall in ward bed availability. These scenarios took no account of the emergence of the new, more transmissible, variant of concern (b.1.1.7). Conclusions Mortality is increased when hospital demand exceeds available capacity. No excess deaths from breaching capacity would be expected under the ‘Optimistic’ scenario. The ‘Middling’ scenario could result in some excess deaths—up to a 0.7% increase relative to the total number of deaths. The ‘Pessimistic’ scenario would have resulted in significant excess deaths. Our sensitivity analysis indicated a range between 49,178 (17% increase) and 103,735 (35.8% increase). Given the new variant, the pessimistic scenario appeared increasingly likely and could have resulted in a substantial increase in the number of COVID-19 deaths. In the event, it would appear that capacity was not breached at any stage at a national level with no excess deaths. it will remain unclear if minor local capacity breaches resulted in any small number of excess deaths.

Description: Background Retrieving gene and disease information from a vast collection of biomedical abstracts to provide doctors with clinical decision support is one of the important research directions of Precision Medicine. Method We propose a novel article retrieval method based on expanded word and co-word analyses, also conducting Cuckoo Search to optimize parameters of the retrieval function. The main goal is to retrieve the abstracts of biomedical articles that refer to treatments. The methods mentioned in this manuscript adopt the BM25 algorithm to calculate the score of abstracts. We, however, propose an improved version of BM25 that computes the scores of expanded words and co-word leading to a composite retrieval function, which is then optimized using the Cuckoo Search. The proposed method aims to find both disease and gene information in the abstract of the same biomedical article. This is to achieve higher relevance and hence score of articles. Besides, we investigate the influence of different parameters on the retrieval algorithm and summarize how they meet various retrieval needs. Results The data used in this manuscript is sourced from medical articles presented in Text Retrieval Conference (TREC): Clinical Decision Support (CDS) Tracks of 2017, 2018, and 2019 in Precision Medicine. A total of 120 topics are tested. Three indicators are employed for the comparison of utilized methods, which are selected among the ones based only on the BM25 algorithm and its improved version to conduct comparable experiments. The results showed that the proposed algorithm achieves better results. Conclusion The proposed method, an improved version of the BM25 algorithm, utilizes both co-word implementation and Cuckoo Search, which has been verified achieving better results on a large number of experimental sets. Besides, a relatively simple query expansion method is implemented in this manuscript. Future research will focus on ontology and semantic networks to expand the query vocabulary.

Description: Background Malignant brain tumor diseases exhibit differences within molecular features depending on the patient’s age. Methods In this work, we use gene mutation data from public resources to explore age specifics about glioma. We use both an explainable clustering as well as classification approach to find and interpret age-based differences in brain tumor diseases. We estimate age clusters and correlate age specific biomarkers. Results Age group classification shows known age specifics but also points out several genes which, so far, have not been associated with glioma classification. Conclusions We highlight mutated genes to be characteristic for certain age groups and suggest novel age-based biomarkers and targets.

Description: Background Colorectal cancer (CRC) is a common malignancy worldwide. Despite being the most common cancer in Singapore, CRC screening rate remains low due to knowledge deficits, social reasons such as inconvenience and a lack of reminder or recommendation. A decision aid (DA) may facilitate an individual’s decision-making to undertake CRC screening by addressing misconceptions and barriers. We postulate that a more person-centred and culturally adapted DA will better serve the local population. The views of the target users are thus needed to develop such a DA. A CRC screening DA prototype has been adapted from an American DA to cater to the Asian users. This study aimed to explore user perspectives on an adapted CRC screening DA-prototype in terms of the design, content and perceived utility. Methods The study used in-depth interviews (IDIs) and focus group discussions (FGDs) to gather qualitative data from English-literate multi-ethnic Asian adults aged 50 years old and above. They had yet to screen for CRC before they were recruited from a public primary care clinic in Singapore. The interviews were audio-recorded, transcribed and analysed to identify emergent themes via thematic analysis. Results This study included 27 participants involved in 5 IDI and 5 FGDs. Participants found the DA easily comprehensible and of appropriate length. They appreciated information about the options and proposed having multi-lingual DAs. The design, in terms of the layout, size and font, was well-accepted but there were suggestions to digitalize the DA. Participants felt that the visuals were useful but there were concerns about modesty due to the realism of the illustration. They would use the DA for information-sharing with their family and for discussion with their doctor for decision making. They preferred the doctor’s recommendation for CRC screening and initiating the use of the DA. Conclusions Participants generally had favourable perceptions of the DA-prototype. A revised DA will be developed based on their feedback. Further input from doctors on the revised DA will be obtained before assessing its effectiveness to increase CRC screening rate in a randomized controlled trial.

Description: Over the last decades, the face of health care has changed dramatically, with big improvements in what is technically feasible. However, there are indicators that the current approach to evaluating evidence in health care is not holistic and hence in the long run, health care will not be sustainable. New conceptual and normative frameworks for the evaluation of health care need to be developed and investigated. The current paper presents a novel framework of justifiable health care and explores how the use of artificial intelligence and big data can contribute to achieving the goals of this framework.

Description: Background Machine learning is a broad term encompassing a number of methods that allow the investigator to learn from the data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient-provider decision making. Methods This systematic literature review was conducted to identify published observational research of employed machine learning to inform decision making at the patient-provider level. The search strategy was implemented and studies meeting eligibility criteria were evaluated by two independent reviewers. Relevant data related to study design, statistical methods and strengths and limitations were identified; study quality was assessed using a modified version of the Luo checklist. Results A total of 34 publications from January 2014 to September 2020 were identified and evaluated for this review. There were diverse methods, statistical packages and approaches used across identified studies. The most common methods included decision tree and random forest approaches. Most studies applied internal validation but only two conducted external validation. Most studies utilized one algorithm, and only eight studies applied multiple machine learning algorithms to the data. Seven items on the Luo checklist failed to be met by more than 50% of published studies. Conclusions A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of machine learning methods to inform patient-provider decision making. There is a need to ensure that multiple machine learning approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that decisions for patient care are being made with the highest quality evidence. Future work should routinely employ ensemble methods incorporating multiple machine learning algorithms.

Description: Background Many patients with atrial fibrillation (AF) remain undiagnosed despite availability of interventions to reduce stroke risk. Predictive models to date are limited by data requirements and theoretical usage. We aimed to develop a model for predicting the 2-year probability of AF diagnosis and implement it as proof-of-concept (POC) in a production electronic health record (EHR). Methods We used a nested case–control design using data from the Indiana Network for Patient Care. The development cohort came from 2016 to 2017 (outcome period) and 2014 to 2015 (baseline). A separate validation cohort used outcome and baseline periods shifted 2 years before respective development cohort times. Machine learning approaches were used to build predictive model. Patients ≥ 18 years, later restricted to age ≥ 40 years, with at least two encounters and no AF during baseline, were included. In the 6-week EHR prospective pilot, the model was silently implemented in the production system at a large safety-net urban hospital. Three new and two previous logistic regression models were evaluated using receiver-operating characteristics. Number, characteristics, and CHA2DS2-VASc scores of patients identified by the model in the pilot are presented. Results After restricting age to ≥ 40 years, 31,474 AF cases (mean age, 71.5 years; female 49%) and 22,078 controls (mean age, 59.5 years; female 61%) comprised the development cohort. A 10-variable model using age, acute heart disease, albumin, body mass index, chronic obstructive pulmonary disease, gender, heart failure, insurance, kidney disease, and shock yielded the best performance (C-statistic, 0.80 [95% CI 0.79–0.80]). The model performed well in the validation cohort (C-statistic, 0.81 [95% CI 0.8–0.81]). In the EHR pilot, 7916/22,272 (35.5%; mean age, 66 years; female 50%) were identified as higher risk for AF; 5582 (70%) had CHA2DS2-VASc score ≥ 2. Conclusions Using variables commonly available in the EHR, we created a predictive model to identify 2-year risk of developing AF in those previously without diagnosed AF. Successful POC implementation of the model in an EHR provided a practical strategy to identify patients who may benefit from interventions to reduce their stroke risk.

Description: Background Artificial intelligence (AI) research is highly dependent on the nature of the data available. With the steady increase of AI applications in the medical field, the demand for quality medical data is increasing significantly. We here describe the development of a platform for providing and sharing digital pathology data to AI researchers, and highlight challenges to overcome in operating a sustainable platform in conjunction with pathologists. Methods Over 3000 pathological slides from five organs (liver, colon, prostate, pancreas and biliary tract, and kidney) in histologically confirmed tumor cases by pathology departments at three hospitals were selected for the dataset. After digitalizing the slides, tumor areas were annotated and overlaid onto the images by pathologists as the ground truth for AI training. To reduce the pathologists’ workload, AI-assisted annotation was established in collaboration with university AI teams. Results A web-based data sharing platform was developed to share massive pathological image data in 2019. This platform includes 3100 images, and 5 pre-processing algorithms for AI researchers to easily load images into their learning models. Discussion Due to different regulations among countries for privacy protection, when releasing internationally shared learning platforms, it is considered to be most prudent to obtain consent from patients during data acquisition. Conclusions Despite limitations encountered during platform development and model training, the present medical image sharing platform can steadily fulfill the high demand of AI developers for quality data. This study is expected to help other researchers intending to generate similar platforms that are more effective and accessible in the future.

Description: Background Ensuring data is of appropriate quality is essential for the secondary use of electronic health records (EHRs) in research and clinical decision support. An effective method of data quality assessment (DQA) is automating data quality rules (DQRs) to replace the time-consuming, labor-intensive manual process of creating DQRs, which is difficult to guarantee standard and comparable DQA results. This paper presents a case study of automatically creating DQRs based on openEHR archetypes in a Chinese hospital to investigate the feasibility and challenges of automating DQA for EHR data. Methods The clinical data repository (CDR) of the Shanxi Dayi Hospital is an archetype-based relational database. Four steps are undertaken to automatically create DQRs in this CDR database. First, the keywords and features relevant to DQA of archetypes were identified via mapping them to a well-established DQA framework, Kahn’s DQA framework. Second, the templates of DQRs in correspondence with these identified keywords and features were created in the structured query language (SQL). Third, the quality constraints were retrieved from archetypes. Fourth, these quality constraints were automatically converted to DQRs according to the pre-designed templates and mapping relationships of archetypes and data tables. We utilized the archetypes of the CDR to automatically create DQRs to meet quality requirements of the Chinese Application-Level Ranking Standard for EHR Systems (CARSES) and evaluated their coverage by comparing with expert-created DQRs. Results We used 27 archetypes to automatically create 359 DQRs. 319 of them are in agreement with the expert-created DQRs, covering 84.97% (311/366) requirements of the CARSES. The auto-created DQRs had varying levels of coverage of the four quality domains mandated by the CARSES: 100% (45/45) of consistency, 98.11% (208/212) of completeness, 54.02% (57/87) of conformity, and 50% (11/22) of timeliness. Conclusion It’s feasible to create DQRs automatically based on openEHR archetypes. This study evaluated the coverage of the auto-created DQRs to a typical DQA task of Chinese hospitals, the CARSES. The challenges of automating DQR creation were identified, such as quality requirements based on semantic, and complex constraints of multiple elements. This research can enlighten the exploration of DQR auto-creation and contribute to the automatic DQA.

Description: Background In this work, we aimed to demonstrate how to utilize the lab test results and other clinical information to support precision medicine research and clinical decisions on complex diseases, with the support of electronic medical record facilities. We defined “clinotypes” as clinical information that could be observed and measured objectively using biomedical instruments. From well-known ‘omic’ problem definitions, we defined problems using clinotype information, including stratifying patients—identifying interested sub cohorts for future studies, mining significant associations between clinotypes and specific phenotypes-diseases, and discovering potential linkages between clinotype and genomic information. We solved these problems by integrating public omic databases and applying advanced machine learning and visual analytic techniques on two-year health exam records from a large population of healthy southern Chinese individuals (size n = 91,354). When developing the solution, we carefully addressed the missing information, imbalance and non-uniformed data annotation issues. Results We organized the techniques and solutions to address the problems and issues above into CPA framework (Clinotype Prediction and Association-finding). At the data preprocessing step, we handled the missing value issue with predicted accuracy of 0.760. We curated 12,635 clinotype-gene associations. We found 147 Associations between 147 chronic diseases-phenotype and clinotypes, which improved the disease predictive performance to AUC (average) of 0.967. We mined 182 significant clinotype-clinotype associations among 69 clinotypes. Conclusions Our results showed strong potential connectivity between the omics information and the clinical lab test information. The results further emphasized the needs to utilize and integrate the clinical information, especially the lab test results, in future PheWas and omic studies. Furthermore, it showed that the clinotype information could initiate an alternative research direction and serve as an independent field of data to support the well-known ‘phenome’ and ‘genome’ researches.

Description: Background Fatigue is a kind of non-specific symptom, which occurs widely in sub-health and various diseases. It is closely related to people's physical and mental health. Due to the lack of objective diagnostic criteria, it is often neglected in clinical diagnosis, especially in the early stage of disease. Many clinical practices and researches have shown that tongue and pulse conditions reflect the body's overall state. Establishing an objective evaluation method for diagnosing disease fatigue and non-disease fatigue by combining clinical symptom, index, and tongue and pulse data is of great significance for clinical treatment timely and effectively. Methods In this study, 2632 physical examination population were divided into healthy controls, sub-health fatigue group, and disease fatigue group. Complex network technology was used to screen out core symptoms and Western medicine indexes of sub-health fatigue and disease fatigue population. Pajek software was used to construct core symptom/index network and core symptom-index combined network. Simultaneously, canonical correlation analysis was used to analyze the objective tongue and pulse data between the two groups of fatigue population and analyze the distribution of tongue and pulse data. Results Some similarities were found in the core symptoms of sub-health fatigue and disease fatigue population, but with different node importance. The node-importance difference indicated that the diagnostic contribution rate of the same symptom to the two groups was different. The canonical correlation coefficient of tongue and pulse data in the disease fatigue group was 0.42 (P 

Description: Background Heart disease is the primary cause of morbidity and mortality in the world. It includes numerous problems and symptoms. The diagnosis of heart disease is difficult because there are too many factors to analyze. What’s more, the misclassification cost could be very high. Methods A cost-sensitive ensemble method was proposed to improve the efficiency of diagnosis and reduce the misclassification cost. The proposed method contains five heterogeneous classifiers: random forest, logistic regression, support vector machine, extreme learning machine and k-nearest neighbor. T-test was used to investigate if the performance of the ensemble was better than individual classifiers and the contribution of Relief algorithm. Results The best performance was achieved by the proposed method according to ten-fold cross validation. The statistical tests demonstrated that the performance of the proposed ensemble was significantly superior to individual classifiers, and the efficiency of classification was distinctively improved by Relief algorithm. Conclusions The proposed ensemble gained significantly better results compared with individual classifiers and previous studies, which implies that it can be used as a promising alternative tool in medical decision making for heart disease diagnosis.

Description: Background Rare Diseases (RDs) are difficult to diagnose. Clinical Decision Support Systems (CDSS) could support the diagnosis for RDs. The Medical Informatics in Research and Medicine (MIRACUM) consortium developed a CDSS for RDs based on distributed clinical data from eight German university hospitals. To support the diagnosis for difficult patient cases, the CDSS uses data from the different hospitals to perform a patient similarity analysis to obtain an indication of a diagnosis. To optimize our CDSS, we conducted a qualitative study to investigate usability and functionality of our designed CDSS. Methods We performed a Thinking Aloud Test (TA-Test) with RDs experts working in Rare Diseases Centers (RDCs) at MIRACUM locations which are specialized in diagnosis and treatment of RDs. An instruction sheet with tasks was prepared that the participants should perform with the CDSS during the study. The TA-Test was recorded on audio and video, whereas the resulting transcripts were analysed with a qualitative content analysis, as a ruled-guided fixed procedure to analyse text-based data. Furthermore, a questionnaire was handed out at the end of the study including the System Usability Scale (SUS). Results A total of eight experts from eight MIRACUM locations with an established RDC were included in the study. Results indicate that more detailed information about patients, such as descriptive attributes or findings, can help the system perform better. The system was rated positively in terms of functionality, such as functions that enable the user to obtain an overview of similar patients or medical history of a patient. However, there is a lack of transparency in the results of the CDSS patient similarity analysis. The study participants often stated that the system should present the user with an overview of exact symptoms, diagnosis, and other characteristics that define two patients as similar. In the usability section, the CDSS received a score of 73.21 points, which is ranked as good usability. Conclusions This qualitative study investigated the usability and functionality of a CDSS of RDs. Despite positive feedback about functionality of system, the CDSS still requires some revisions and improvement in transparency of the patient similarity analysis.

Description: Background Burn is one of the most brutal harms to the human body and mind and its wide-ranging complications have many adverse effects on the patients’ quality of life. The present study was conducted to investigate the effect of rehabilitation education through social media on burn patients’ quality of life. Methods The present randomized, controlled, clinical trial was conducted on 60 patients admitted to Imam Reza Hospital Burn Center in the city of Mashhad, Iran, who were randomly assigned to either the intervention or control groups (n = 30 per group). The researcher then created a WhatsApp channel to provide educational content and a WhatsApp group for burns patients to join and get their questions answered. The intervention group patients pursued their post-discharge education through the social media for a month. The control group patients received their discharge education according to the ward’s routine procedures through pamphlets and face-to-face training by the personnel. As the study’s main variable, the Burn Specific Health Scale-Brief was completed by both groups before and 1 and 2 months after the intervention. Data were analyzed using the ANCOVA and repeated-measures ANOVA. Results There was no significant differences between the intervention and control groups in terms of the QOL score and any of the domains at baseline. The results indicated the significant effect of the intervention both 1 and 2 months post-intervention on the QOL score and all the domains (P 

Description: Given a k-node pattern graph H and an n-node host graph G, the subgraph counting problem asks to compute the number of copies of H in G. In this work we address the following question: can we count the copies of H faster if G is sparse? We answer in the affirmative by introducing a novel tree-like decomposition for directed acyclic graphs, inspired by the classic tree decomposition for undirected graphs. This decomposition gives a dynamic program for counting the homomorphisms of H in G by exploiting the degeneracy of G, which allows us to beat the state-of-the-art subgraph counting algorithms when G is sparse enough. For example, we can count the induced copies of any k-node pattern H in time $$2^{O(k^2)} O(n^{0.25k + 2} log n)$$ 2 O ( k 2 ) O ( n 0.25 k + 2 log n ) if G has bounded degeneracy, and in time $$2^{O(k^2)} O(n^{0.625k + 2} log n)$$ 2 O ( k 2 ) O ( n 0.625 k + 2 log n ) if G has bounded average degree. These bounds are instantiations of a more general result, parameterized by the degeneracy of G and the structure of H, which generalizes classic bounds on counting cliques and complete bipartite graphs. We also give lower bounds based on the Exponential Time Hypothesis, showing that our results are actually a characterization of the complexity of subgraph counting in bounded-degeneracy graphs.

Description: Background Mining massive prescriptions in Traditional Chinese Medicine (TCM) accumulated in the lengthy period of several thousand years to discover essential herbal groups for distinct efficacies is of significance for TCM modernization, thus starting to draw attentions recently. However, most existing methods for the task treat herbs with different surface forms orthogonally and determine efficacy-specific herbal groups based on the raw frequencies an herbal group occur in a collection of prescriptions. Such methods entirely overlook the fact that prescriptions in TCM are formed empirically by different people at different historical stages, and thus full of herbs with different surface forms expressing the same material, or even noisy and redundant herbs. Methods We propose a two-stage approach for efficacy-specific herbal group detection from prescriptions in TCM. For the first stage we devise a hierarchical attentive neural network model to capture essential herbs in a prescription for its efficacy, where herbs are encoded with dense real-valued vectors learned automatically to identify their differences on the semantical level. For the second stage, frequent patterns are mined to discover essential herbal groups for an efficacy from distilled prescriptions obtained in the first stage. Results We verify the effectiveness of our proposed approach from two aspects, the first one is the ability of the hierarchical attentive neural network model to distill a prescription, and the second one is the accuracy in discovering efficacy-specific herbal groups. Conclusion The experimental results demonstrate that the hierarchical attentive neural network model is capable to capture herbs in a prescription essential to its efficacy, and the distilled prescriptions significantly could improve the performance of efficacy-specific herbal group detection.

Description: Background The Thai medical application for patient triage, namely Triagist, is an mHealth application designed to support the pre-hospital process. However, since the functions of the application that are necessary for the pre-hospital process have been found not to be fully developed, the addition of a back-end system has been considered to increase its performance and usability. Objective To determine the ability of the previous version to effectively manage the pre-hospital process and analyse the current problems with the pre-hospital operation. Therefore, the new system was developed to support the connection of dispatch centres or operational centres to the Triagist mobile application and system evaluation. Method Design thinking methodology was used to analyse, design and develop a patient triage system to support the pre-hospital process in Thailand based on users’ requirements. 68 active members of the rescue teams and emergency medical staff in Chiang Mai and Lampang provinces were recruited to test the reliability of the system based on a prototype application. Results The new medical mobile application for patient triage in Thailand was validated for use due to containing the two essential functions of Initial Dispatch Code (IDC) geolocation and IDC management. When the system was tested by emergency staff who were responsible for using it, those with the least experience were found to use it better than their highly experienced colleagues. Moreover, in cases where the system had been implemented, it was found to determine the frequency of symptoms, the time period during which cases occurred, and the density of cases in each area. Conclusion This system, which has been developed based on the use of smart technology, will play an important role in supporting emergency services in Thailand by enhancing the efficiency of the pre-hospital process. Emergency centres will receive IDC information from the geolocation system so that they can determine patients’ location without undue delay. Emergency services will be able to rapidly prepare the necessary resources and administrative tasks will be supported by linking the dispatch centre to central rescue teams.

Description: Background Despite a substantial increase in the adoption of electronic medical records (EMRs) in primary health care settings, the use of advanced EMR features is limited. Several studies have identified both barriers and facilitating factors that influence primary care physicians’ (PCPs) use of advanced EMR features and the maturation of their EMR use. The purpose of this study is to explore and identify the factors that impact PCPs’ mature use of EMRs. Methods A systematic review was conducted in accordance with the Cochrane Handbook. The MEDLINE, Embase, and PsycINFO electronic databases were searched from 1946 to June 13, 2019. Two independent reviewers screened the studies for eligibility; to be included, studies had to address factors influencing PCPs’ mature use of EMRs. A narrative synthesis was conducted to collate study findings and to report on patterns identified across studies. The quality of the studies was also appraised. Results Of the 1893 studies identified, 14 were included in this study. Reported factors that influenced PCPs’ mature use of EMRs fell into one of the following 5 categories: technology, people, organization, resources, and policy. Concerns about the EMR system’s functionality, lack of physician awareness of EMR functionality, limited physician availability to learn more about EMRs, the habitual use of successfully completing clinical tasks using only basic EMR features, business-oriented organizational objectives, lack of vendor training, limited resource availability, and lack of physician readiness were reported as barriers to PCPs’ mature use of EMRs. The motivation of physicians, user satisfaction, coaching and peer mentoring, EMR experience, gender, physician perception, transition planning for changes in roles and work processes, team-based care, adequate technical support and training, sharing resources, practices affiliated with an integrated delivery system, financial incentives, and policies to increase EMR use all had a favorable impact on PCPs’ use of advanced EMR features. Conclusions By using a narrative synthesis to synthesize the evidence, we identified interrelated factors influencing the mature use of EMRs by PCPs. The findings underline the need to provide adequate training and policies that facilitate the mature use of EMRs by PCPs. Trial registration: PROSPERO CRD42019137526.

Description: A resolving set S of a graph G is a subset of its vertices such that no two vertices of G have the same distance vector to S. The Metric Dimension problem asks for a resolving set of minimum size, and in its decision form, a resolving set of size at most some specified integer. This problem is NP-complete, and remains so in very restricted classes of graphs. It is also W[2]-complete with respect to the size of the solution. Metric Dimension has proven elusive on graphs of bounded treewidth. On the algorithmic side, a polynomial time algorithm is known for trees, and even for outerplanar graphs, but the general case of treewidth at most two is open. On the complexity side, no parameterized hardness is known. This has led several papers on the topic to ask for the parameterized complexity of Metric Dimension with respect to treewidth. We provide a first answer to the question. We show that Metric Dimension parameterized by the treewidth of the input graph is W[1]-hard. More refinedly we prove that, unless the Exponential Time Hypothesis fails, there is no algorithm solving Metric Dimension in time $$f(ext {pw})n^{o(ext {pw})}$$ f ( pw ) n o ( pw ) on n-vertex graphs of constant degree, with $$ext {pw}$$ pw the pathwidth of the input graph, and f any computable function. This is in stark contrast with an FPT algorithm of Belmonte et al. (SIAM J Discrete Math 31(2):1217–1243, 2017) with respect to the combined parameter $$ext {tl}+Delta$$ tl + Δ , where $$ext {tl}$$ tl is the tree-length and $$Delta$$ Δ the maximum-degree of the input graph.

Description: Background Taking care of chronic or long-term patients at home is an arduous task. Non-professional caregivers suffer the consequences of doing so, especially in terms of their mental health. Performing some simple activities through a mobile phone app may improve their mindset and consequently increase their positivity. However, each caregiver may need support in different aspects of positive mental health. In this paper, a method is defined to calculate the utility of a set of activities for a particular caregiver in order to personalize the intervention plan proposed in the app. Methods Based on the caregivers’ answers to a questionnaire, a modular averaging method is used to calculate the personal level of competence in each positive mental health factor. A reward-penalty scoring procedure then assigns an overall impact value to each activity. Finally, the app ranks the activities using this impact value. Results The results of this new personalization method are provided based on a pilot test conducted on 111 caregivers. The results indicate that a conjunctive average is appropriate at the first stage and that reward should be greater than penalty in the second stage. Conclusions The method presented is able to personalize the intervention plan by determining the best order of carrying out the activities for each caregiver, with the aim of avoiding a high level of deterioration in any factor.

Description: Background Radiation Therapy (RT) is a common treatment after breast cancer surgery and a complex process using high energy X-rays to eradicate cancer cells, important in reducing the risk of local recurrence. The high-tech environment and unfamiliar nature of RT can affect the patient’s experience of the treatment. Misconceptions or lack of knowledge about RT processes can increase levels of anxiety and enhance feelings of being unprepared at the beginning of treatment. Moreover, the waiting time is often quite long. The primary aim of this study will be to evaluate whether a digital information tool with VR-technology and preparatory information can decrease distress as well as enhance the self-efficacy and health literacy of patients affected by breast cancer before, during, and after RT. A secondary aim will be to explore whether the digital information tool increase patient flow while maintaining or increasing the quality of care. Method The study is a prospective and longitudinal RCT study with an Action Research participatory design approach including mixed-methods data collection, i.e., standardised instruments, qualitative interviews (face-to-face and telephone) with a phenomenological hermeneutical approach, diaries, observations, and time measurements, and scheduled to take place from autumn 2020 to spring 2022. The intervention group (n = 80), will receive standard care and information (oral and written) and the digital information tool; and the control group (n = 80), will receive standard care and information (oral and written). Study recruitment and randomisation will be completed at two centres in the west of Sweden. Discussion Research in this area is scarce and, to our knowledge, only few previous studies examine VR as a tool for increasing preparedness for patients with breast cancer about to undergo RT that also includes follow-ups six months after completed treatment. The participatory approach and design will safeguard the possibilities to capture the patient perspective throughout the development process, and the RCT design supports high research quality. Digitalisation brings new possibilities to provide safe, person-centred information that also displays a realistic picture of RT treatment and its contexts. The planned study will generate generalisable knowledge of relevance in similar health care contexts. Trial registration: ClinicalTrials.gov Identifier: NCT04394325. Registered May 19, 2020. Prospectively registered.

Description: Background Currently the diagnosis of shoulder instability, particularly in children, is difficult and can take time. These diagnostic delays can lead to poorer outcome and long-term complications. A Diagnostic Decision Support System (DDSS) has the potential to reduce time to diagnosis and improve outcomes for patients. The aim of this study was to develop a concept map for a future DDSS in shoulder instability. Methods A modified nominal focus group technique, involving three clinical vignettes, was used to elicit physiotherapists decision-making processes. Results Twenty-five physiotherapists, (18F:7 M) from four separate clinical sites participated. The themes identified related to ‘Variability in diagnostic processes and lack of standardised practice’ and ‘Knowledge and attitudes towards novel technologies for facilitating assessment and clinical decision making’. Conclusion No common structured approach towards assessment and diagnosis was identified. Lack of knowledge, perceived usefulness, access and cost were identified as barriers to adoption of new technology. Based on the information elicited a conceptual design of a future DDSS has been proposed. Work to develop a systematic approach to assessment, classification and diagnosis is now proposed. Trial Registraty This was not a clinical trial and so no clinical trial registry is needed.

Description: Background Previous studies showed that transitional care reduces the complication rate and readmission rate and improves the quality of life in kidney transplant receipts, nevertheless, in fact there are no standard evaluation indexes and debatable scientific of existing indexes in kidney transplant recipients. Therefore, the aim of this study was to construct an evaluation index system to assess the effects of transitional care in kidney transplant recipients. Methods Based on Omaha system, an initial evaluation index system about the effects of transitional care in kidney transplant recipients was drafted by the literature review and semi-structured interview. Two rounds of correspondence were conducted in 19 experts and the analytic hierarchy process (AHP) was used to calculate the weights of all indexes. Results Five first-level indexes, sixteen second-level indexes, and forty-eight third-level indexes were selected in the initial evaluation index system. The authority coefficient of two-round expert consultations was 0.90 and coordination coefficients of indexes ranged from 0.24 to 0.34. Conclusion The established evaluation index system for the effectiveness of transitional care for kidney transplant recipients was scientific and reliable. Furthermore, it would be a potential method to evaluate effects of transitional care in kidney transplant recipients after further examination.

Description: Background Prediction of neonatal deaths in NICUs is important for benchmarking and evaluating healthcare services in NICUs. Application of machine learning techniques can improve physicians’ ability to predict the neonatal deaths. The aim of this study was to present a neonatal death risk prediction model using machine learning techniques. Methods This study was conducted in Tehran, Iran in two phases. Initially, important risk factors in neonatal death were identified and then several machine learning models including Artificial Neural Network (ANN), decision tree (Random Forest (RF), C5.0 and CHART tree), Support Vector Machine (SVM), Bayesian Network and Ensemble models were developed. Finally, we prospectively applied these models to predict neonatal death in a NICU and followed up the neonates to compare the outcomes of these neonates with real outcomes. Results 17 factors were considered important in neonatal mortality prediction. The highest Area Under the Curve (AUC) was achieved for the SVM and Ensemble models with 0.98. The best precision and specificity were 0.98 and 0.94, respectively for the RF model. The highest accuracy, sensitivity and F-score were achieved for the SVM model with 0.94, 0.95 and 0.96, respectively. The best performance of models in prospective evaluation was for the ANN, C5.0 and CHAID tree models. Conclusion Using the developed machine learning models can help physicians predict the neonatal deaths in NICUs.

Description: We study algorithmic properties of the graph class $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e , that is, graphs that can be turned into a chordal graph by adding at most k edges or, equivalently, the class of graphs of fill-in at most k. It appears that a number of fundamental intractable optimization problems being parameterized by k admit subexponential algorithms on graphs from $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e . More precisely, we identify a large class of optimization problems on $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e solvable in time $$2^{{mathcal{O}}(sqrt{k}log k)}cdot n^{{mathcal{O}}(1)}$$ 2 O ( k log k ) · n O ( 1 ) . Examples of the problems from this class are finding an independent set of maximum weight, finding a feedback vertex set or an odd cycle transversal of minimum weight, or the problem of finding a maximum induced planar subgraph. On the other hand, we show that for some fundamental optimization problems, like finding an optimal graph coloring or finding a maximum clique, are FPT on $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e when parameterized by k but do not admit subexponential in k algorithms unless ETH fails. Besides subexponential time algorithms, the class of $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e graphs appears to be appealing from the perspective of kernelization (with parameter k). While it is possible to show that most of the weighted variants of optimization problems do not admit polynomial in k kernels on $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e graphs, this does not exclude the existence of Turing kernelization and kernelization for unweighted graphs. In particular, we construct a polynomial Turing kernel for Weighted Clique on $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e graphs. For (unweighted) Independent Set we design polynomial kernels on two interesting subclasses of $${extsc {Chordal}}{-ke}$$ C H O R D A L - k e , namely, $${extsc {Interval}}{-ke}$$ I N T E R V A L - k e and $${extsc {Split}}{-ke}$$ S P L I T - k e graphs.

Description: Background Screening carotid B-mode ultrasonography is a frequently used method to detect subjects with carotid atherosclerosis (CAS). Due to the asymptomatic progression of most CAS patients, early identification is challenging for clinicians, and it may trigger ischemic stroke. Recently, machine learning has shown a strong ability to classify data and a potential for prediction in the medical field. The combined use of machine learning and the electronic health records of patients could provide clinicians with a more convenient and precise method to identify asymptomatic CAS. Methods Retrospective cohort study using routine clinical data of medical check-up subjects from April 19, 2010 to November 15, 2019. Six machine learning models (logistic regression [LR], random forest [RF], decision tree [DT], eXtreme Gradient Boosting [XGB], Gaussian Naïve Bayes [GNB], and K-Nearest Neighbour [KNN]) were used to predict asymptomatic CAS and compared their predictability in terms of the area under the receiver operating characteristic curve (AUCROC), accuracy (ACC), and F1 score (F1). Results Of the 18,441 subjects, 6553 were diagnosed with asymptomatic CAS. Compared to DT (AUCROC 0.628, ACC 65.4%, and F1 52.5%), the other five models improved prediction: KNN + 7.6% (0.704, 68.8%, and 50.9%, respectively), GNB + 12.5% (0.753, 67.0%, and 46.8%, respectively), XGB + 16.0% (0.788, 73.4%, and 55.7%, respectively), RF + 16.6% (0.794, 74.5%, and 56.8%, respectively) and LR + 18.1% (0.809, 74.7%, and 59.9%, respectively). The highest achieving model, LR predicted 1045/1966 cases (sensitivity 53.2%) and 3088/3566 non-cases (specificity 86.6%). A tenfold cross-validation scheme further verified the predictive ability of the LR. Conclusions Among machine learning models, LR showed optimal performance in predicting asymptomatic CAS. Our findings set the stage for an early automatic alarming system, allowing a more precise allocation of CAS prevention measures to individuals probably to benefit most.

Description: Background Despite growing evidence that deprescribing can improve clinical outcomes, quality of life and reduce the likelihood of adverse drug events, the practice is not widespread, particularly in hospital settings. Clinical risk assessment tools, like the Drug Burden Index (DBI), can help prioritise patients for medication review and prioritise medications to deprescribe, but are not integrated within routine care. The aim of this study was to conduct formative usability testing of a computerised decision support (CDS) tool, based on DBI, to identify modifications required to the tool prior to trialling in practice. Methods Our CDS tool comprised a DBI MPage in the electronic medical record (clinical workspace) that facilitated review of a patient’s DBI and medication list, access to deprescribing resources, and the ability to deprescribe. Two rounds of scenario-based formative usability testing with think-aloud protocol were used. Seventeen end-users participated in the testing, including junior and senior doctors, and pharmacists. Results Participants expressed positive views about the DBI CDS tool but testing revealed a number of clear areas for improvement. These primarily related to terminology used (i.e. what is a DBI and how is it calculated?), and consistency of functionality and display. A key finding was that users wanted the CDS tool to look and function in a similar way to other decision support tools in the electronic medical record. Modifications were made to the CDS tool in response to user feedback. Conclusion Usability testing proved extremely useful for identifying components of our CDS tool that were confusing, difficult to locate or to understand. We recommend usability testing be adopted prior to implementation of any digital health intervention. We hope our revised CDS tool equips clinicians with the knowledge and confidence to consider discontinuation of inappropriate medications in routine care of hospitalised patients. In the next phase of our project, we plan to pilot test the tool in practice to evaluate its uptake and effectiveness in supporting deprescribing in routine hospital care.