ALBERT

Description: Background Occlusions of intravenous (IV) tubing can prevent vital and time-critical medication or solutions from being delivered into the bloodstream of patients receiving IV therapy. At low flow rates (≤ 1 ml/h) the alarm delay (time to an alert to the user) can be up to 2 h using conventional pressure threshold algorithms. In order to reduce alarm delays we developed and evaluated the performance of two new real-time occlusion detection algorithms and one co-occlusion detector that determines the correlation in trends in pressure changes for multiple pumps. Methods Bench-tested experimental runs were recorded in triplicate at rates of 1, 2, 4, 8, 16, and 32 ml/h. Each run consisted of 10 min of non-occluded infusion followed by a period of occluded infusion of 10 min or until a conventional occlusion alarm at 400 mmHg occurred. The first algorithm based on binary logistic regression attempts to detect occlusions based on the pump’s administration rate Q(t) and pressure sensor readings P(t). The second algorithm continuously monitored whether the actual variation in the pressure exceeded a threshold of 2 standard deviations (SD) above the baseline pressure. When a pump detected an occlusion using the SD algorithm, a third algorithm correlated the pressures of multiple pumps to detect the presence of a shared occlusion. The algorithms were evaluated using 6 bench-tested baseline single-pump occlusion scenarios, 9 single-pump validation scenarios and 7 multi-pump co-occlusion scenarios (i.e. with flow rates of 1 + 1, 1 + 2, 1 + 4, 1 + 8, 1 + 16, and 1 + 32 ml/h respectively). Alarm delay was the primary performance measure. Results In the baseline single-pump occlusion scenarios, the overall mean ± SD alarm delay of the regression and SD algorithms were 1.8 ± 0.8 min and 0.4 ± 0.2 min, respectively. Compared to the delay of the conventional alarm this corresponds to a mean time reduction of 76% (P = 0.003) and 95% (P = 0.001), respectively. In the validation scenarios the overall mean ± SD alarm delay of the regression and SD algorithms were respectively 1.8 ± 1.6 min and 0.3 ± 0.2 min, corresponding to a mean time reduction of 77% and 95%. In the multi-pump scenarios a correlation 〉 0.8 between multiple pump pressures after initial occlusion detection by the SD algorithm had a mean ± SD alarm delay of 0.4 ± 0.2 min. In 2 out of the 9 validation scenarios an occlusion was not detected by the regression algorithm before a conventional occlusion alarm occurred. Otherwise no occlusions were missed. Conclusions In single pumps, both the regression and SD algorithm considerably reduced alarm delay compared to conventional pressure limit-based detection. The SD algorithm appeared to be more robust than the regression algorithm. For multiple pumps the correlation algorithm reliably detected co-occlusions. The latter may be used to localize the segment of tubing in which the occlusion occurs. Trial registration Not applicable.

Description: Background ANAT is a Cytoscape plugin for the inference of functional protein–protein interaction networks in yeast and human. It is a flexible graphical tool for scientists to explore and elucidate the protein–protein interaction pathways of a process under study. Results Here we present ANAT3.0, which comes with updated PPI network databases of 544,455 (human) and 155,504 (yeast) interactions, and a new machine-learning layer for refined network elucidation. Together they improve network reconstruction to more than twofold increase in the quality of reconstructing known signaling pathways from KEGG. Conclusions ANAT3.0 includes improved network reconstruction algorithms and more comprehensive protein–protein interaction networks than previous versions. ANAT is available for download on the Cytoscape Appstore and at https://www.cs.tau.ac.il/~bnet/ANAT/.

Description: Background Molecular interaction networks summarize complex biological processes as graphs, whose structure is informative of biological function at multiple scales. Simultaneously, omics technologies measure the variation or activity of genes, proteins, or metabolites across individuals or experimental conditions. Integrating the complementary viewpoints of biological networks and omics data is an important task in bioinformatics, but existing methods treat networks as discrete structures, which are intrinsically difficult to integrate with continuous node features or activity measures. Graph neural networks map graph nodes into a low-dimensional vector space representation, and can be trained to preserve both the local graph structure and the similarity between node features. Results We studied the representation of transcriptional, protein–protein and genetic interaction networks in E. coli and mouse using graph neural networks. We found that such representations explain a large proportion of variation in gene expression data, and that using gene expression data as node features improves the reconstruction of the graph from the embedding. We further proposed a new end-to-end Graph Feature Auto-Encoder framework for the prediction of node features utilizing the structure of the gene networks, which is trained on the feature prediction task, and showed that it performs better at predicting unobserved node features than regular MultiLayer Perceptrons. When applied to the problem of imputing missing data in single-cell RNAseq data, the Graph Feature Auto-Encoder utilizing our new graph convolution layer called FeatGraphConv outperformed a state-of-the-art imputation method that does not use protein interaction information, showing the benefit of integrating biological networks and omics data with our proposed approach. Conclusion Our proposed Graph Feature Auto-Encoder framework is a powerful approach for integrating and exploiting the close relation between molecular interaction networks and functional genomics data.

Description: Machine learning and artificial intelligence have entered biomedical decision-making for diagnostics, prognostics, or therapy recommendations. However, these methods need to be interpreted with care because of the severe consequences for patients. In contrast to human decision-making, computational models typically make a decision also with low confidence. Machine learning with abstention better reflects human decision-making by introducing a reject option for samples with low confidence. The abstention intervals are typically symmetric intervals around the decision boundary. In the current study, we use asymmetric abstention intervals, which we demonstrate to be better suited for biomedical data that is typically highly imbalanced. We evaluate symmetric and asymmetric abstention on three real-world biomedical datasets and show that both approaches can significantly improve classification performance. However, asymmetric abstention rejects as many or fewer samples compared to symmetric abstention and thus, should be used in imbalanced data.

Description: Background Health systems globally are investing in integrating secure messaging platforms for virtual care in clinical practice. Implementation science is essential for adoption, scale-up, spread and maintenance of complex evidence-based solutions in clinics with evolving priorities. In response, the mobile Health (mHealth) Research Group modified the existing consolidated framework for implementation research (CFIR) to evaluate implementation of virtual health tools in clinical settings. WelTel® is an evidence-based digital health platform widely deployed in various geographical and health contexts. The objective is to identify the facilitators and barriers for implementing WelTel and to assess the application of the mCFIR tool in facilitating focus groups in different geographical and health settings. Methods Both qualitative and descriptive quantitative approaches were employed. Six mCFIR sessions were held in three countries with 51 key stakeholders. The mCFIR tool consists of 5 Domains and 25 constructs and was distributed through Qualtrics Experience Management (XM). “Performance” and “Importance” scores were valued on a scale of 0 to 10 (Mean ± SD). Descriptive analysis was conducted using R computing software. NVivo 12 Pro software was used to analyze mCFIR responses and to generate themes from the participants’ input. Results We observed a parallel trend in the scores of Importance and Performance. Of the five Domains, Domain 4 (End-user Characteristics) and Domain 3 (Inner Settings) scored highest in Importance (8.9 ± 0.5 and 8.6 ± 0.6, respectively) and Performance (7.6 ± 0.7 and 7.2 ± 1.3, respectively) for all sites. Domain 2 (Outer Setting) scored the lowest in both Importance and Performance for all sites (7.6 ± 0.4 and 5.6 ± 1.8). The thematic analysis produced the following themes: for areas of strengths, the themes brought up were timely diagnosis and response, cost-effectiveness, and user-friendliness. As for areas for improvement, the themes discussed were training, phone accessibility, stakeholder engagement, and literacy. Conclusion The mCFIR tool allowed for a comprehensive understanding of the barriers and facilitators to the implementation, reach, and scale-up of digital health tools. Amongst several important findings, we observed the value of bringing the perspectives of both end users (HCPs and patients) to the table across Domains. Trial Registration: NCT02603536 – November 11, 2015: WelTelOAKTREE: Text Messaging to Support Patients With HIV/AIDS in British Columbia (WelTelOAKTREE). NCT01549457 – March 9, 2012: TB mHealth Study—Use of Cell Phones to Improve Compliance in Patients on LTBI Treatment.

Description: Background The genetic basis of phenotypic traits is highly variable and usually divided into mono-, oligo- and polygenic inheritance classes. Relatively few traits are known to be monogenic or oligogeneic. The majority of traits are considered to have a polygenic background. To what extent there are mixtures between these classes is unknown. The rapid advancement of genomic techniques makes it possible to directly map large amounts of genomic markers (GWAS) and predict unknown phenotypes (GWP). Most of the multi-marker methods for GWAS and GWP falls into one of two regularization frameworks. The first framework is based on $$ell _1$$ ℓ 1 -norm regularization (e.g. the LASSO) and is suitable for mono- and oligogenic traits, whereas the second framework regularize with the $$ell _2$$ ℓ 2 -norm (e.g. ridge regression; RR) and thereby is favourable for polygenic traits. A general framework for mixed inheritance is lacking. Results We have developed a proximal operator algorithm based on the recent LAVA regularization method that jointly performs $$ell _1$$ ℓ 1 - and $$ell _2$$ ℓ 2 -norm regularization. The algorithm is built on the alternating direction method of multipliers and proximal translation mapping (LAVA ADMM). When evaluated on the simulated QTLMAS2010 data, it is shown that the LAVA ADMM together with Bayesian optimization of the regularization parameters provides an efficient approach with lower test prediction mean-squared-error (65.89) than the LASSO (66.11), Ridge regression (83.41) and Elastic net (66.11). For the real pig data the test MSE of the LAVA ADMM is 0.850 compared to the LASSO, RR and EN with 0.875, 0.853 and 0.853, respectively. Conclusions This study presents the LAVA ADMM that is capable of joint modelling of monogenic major genetic effects and polygenic minor genetic effects which can be used for both genome-wide assoiciation and prediction purposes. The statistical evaluations based on both simulated and real pig data set shows that the LAVA ADMM has better prediction properies than the LASSO, RR and EN. Julia code for the LAVA ADMM is available at: https://github.com/patwa67/LAVAADMM.

Description: Background Recent development of single cell sequencing technologies has made it possible to identify genes with different expression (DE) levels at the cell type level between different groups of samples. In this article, we propose to borrow information through known biological networks to increase statistical power to identify differentially expressed genes (DEGs). Results We develop MRFscRNAseq, which is based on a Markov random field (MRF) model to appropriately accommodate gene network information as well as dependencies among cell types to identify cell-type specific DEGs. We implement an Expectation-Maximization (EM) algorithm with mean field-like approximation to estimate model parameters and a Gibbs sampler to infer DE status. Simulation study shows that our method has better power to detect cell-type specific DEGs than conventional methods while appropriately controlling type I error rate. The usefulness of our method is demonstrated through its application to study the pathogenesis and biological processes of idiopathic pulmonary fibrosis (IPF) using a single-cell RNA-sequencing (scRNA-seq) data set, which contains 18,150 protein-coding genes across 38 cell types on lung tissues from 32 IPF patients and 28 normal controls. Conclusions The proposed MRF model is implemented in the R package MRFscRNAseq available on GitHub. By utilizing gene-gene and cell-cell networks, our method increases statistical power to detect differentially expressed genes from scRNA-seq data.

Description: Background One of the important components of the health system is the emergency medical services (EMS) system. The EMS system was implemented at Kerman University of Medical Sciences teaching hospitals to communicate the situation of patients being transferred to the hospital by EMS and to provide facilities tailored to the patient's condition. The objective of this study was to investigate the impact of the EMS system on the patient care process and the workflow of users. Methods The hospital information system (HIS) report was used to investigate the impact of the EMS system on the patient care process and a questionnaire was distributed among 244 participants to determine its impact on the workflow of the users. Mann–Whitney U was used to analyze HIS reports, and Chi-square was used to analyze the data collected by questionnaires. Results The EMS system reduced the patient's stay in hospital by an average of 3 h and 45 min. It also increased the number of patients' discharge from the emergency room to 2.2% and reduced the death rate by 1.3% (p 

Description: Background This study focuses on the task of supervised prediction of aging-related genes from -omics data. Unlike gene expression methods for this task that capture aging-specific information but ignore interactions between genes (i.e., their protein products), or protein–protein interaction (PPI) network methods for this task that account for PPIs but the PPIs are context-unspecific, we recently integrated the two data types into an aging-specific PPI subnetwork, which yielded more accurate aging-related gene predictions. However, a dynamic aging-specific subnetwork did not improve prediction performance compared to a static aging-specific subnetwork, despite the aging process being dynamic. This could be because the dynamic subnetwork was inferred using a naive Induced subgraph approach. Instead, we recently inferred a dynamic aging-specific subnetwork using a methodologically more advanced notion of network propagation (NP), which improved upon Induced dynamic aging-specific subnetwork in a different task, that of unsupervised analyses of the aging process. Results Here, we evaluate whether our existing NP-based dynamic subnetwork will improve upon the dynamic as well as static subnetwork constructed by the Induced approach in the considered task of supervised prediction of aging-related genes. The existing NP-based subnetwork is unweighted, i.e., it gives equal importance to each of the aging-specific PPIs. Because accounting for aging-specific edge weights might be important, we additionally propose a weighted NP-based dynamic aging-specific subnetwork. We demonstrate that a predictive machine learning model trained and tested on the weighted subnetwork yields higher accuracy when predicting aging-related genes than predictive models run on the existing unweighted dynamic or static subnetworks, regardless of whether the existing subnetworks were inferred using NP or the Induced approach. Conclusions Our proposed weighted dynamic aging-specific subnetwork and its corresponding predictive model could guide with higher confidence than the existing data and models the discovery of novel aging-related gene candidates for future wet lab validation.

Description: Background Current alignment tools typically lack an explicit model of indel evolution, leading to artificially short inferred alignments (i.e., over-alignment) due to inconsistencies between the indel history and the phylogeny relating the input sequences. Results We present a new progressive multiple sequence alignment tool ProPIP. The process of insertions and deletions is described using an explicit evolutionary model—the Poisson Indel Process or PIP. The method is based on dynamic programming and is implemented in a frequentist framework. The source code can be compiled on Linux, macOS and Microsoft Windows platforms. The algorithm is implemented in C++ as standalone program. The source code is freely available on GitHub at https://github.com/acg-team/ProPIP and is distributed under the terms of the GNU GPL v3 license. Conclusions The use of an explicit indel evolution model allows to avoid over-alignment, to infer gaps in a phylogenetically consistent way and to make inferences about the rates of insertions and deletions. Instead of the arbitrary gap penalties, the parameters used by ProPIP are the insertion and deletion rates, which have biological interpretation and are contextualized in a probabilistic environment. As a result, indel rate settings may be optimised in order to infer phylogenetically meaningful gap patterns.