ALBERT

Description: While cross-spectral and information-theoretic approaches are widely used for the multivariate analysis of physiological time series, their combined utilization is far less developed in the literature. This study introduces a framework for the spectral decomposition of multivariate information measures, which provides frequency-specific quantifications of the information shared between a target and two source time series and of its expansion into amounts related to how the sources contribute to the target dynamics with unique, redundant and synergistic information. The framework is illustrated in simulations of linearly interacting stochastic processes, showing how it allows us to retrieve amounts of information shared by the processes within specific frequency bands which are otherwise not detectable by time-domain information measures, as well as coupling features which are not detectable by spectral measures. Then, it is applied to the time series of heart period, systolic and diastolic arterial pressure and respiration variability measured in healthy subjects monitored in the resting supine position and during head-up tilt. We show that the spectral measures of unique, redundant and synergistic information shared by these variability series, integrated within specific frequency bands of physiological interest and reflect the mechanisms of short-term regulation of cardiovascular and cardiorespiratory oscillations and their alterations induced by the postural stress. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

Description: Stress test electrocardiogram (ECG) analysis is widely used for coronary artery disease (CAD) diagnosis despite its limited accuracy. Alterations in autonomic modulation of cardiac electrical activity have been reported in CAD patients during acute ischemia. We hypothesized that those alterations could be reflected in changes in ventricular repolarization dynamics during stress testing that could be measured through QT interval variability (QTV). However, QTV is largely dependent on RR interval variability (RRV), which might hinder intrinsic ventricular repolarization dynamics. In this study, we investigated whether different markers accounting for low-frequency (LF) oscillations of QTV unrelated to RRV during stress testing could be used to separate patients with and without CAD. Power spectral density of QTV unrelated to RRV was obtained based on time-frequency coherence estimation. Instantaneous LF power of QTV and QTV unrelated to RRV were obtained. LF power of QTV unrelated to RRV normalized by LF power of QTV was also studied. Stress test ECG of 100 patients were analysed. Patients referred to coronary angiography were classified into non-CAD or CAD group. LF oscillations in QTV did not show significant differences between CAD and non-CAD groups. However, LF oscillations in QTV unrelated to RRV were significantly higher in the CAD group as compared with the non-CAD group when measured during the first phases of exercise and last phases of recovery. ROC analysis of these indices revealed area under the curve values ranging from 61 to 73%. Binomial logistic regression analysis revealed LF power of QTV unrelated to RRV, both during the first phase of exercise and last phase of recovery, as independent predictors of CAD. In conclusion, this study highlights the importance of removing the influence of RRV when measuring QTV during stress testing for CAD identification and supports the added value of LF oscillations of QTV unrelated to RRV to diagnose CAD from the first minutes of exercise. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: Cardiac magnetic resonance (CMR) imaging is a valuable modality in the diagnosis and characterization of cardiovascular diseases, since it can identify abnormalities in structure and function of the myocardium non-invasively and without the need for ionizing radiation. However, in clinical practice, it is commonly acquired as a collection of separated and independent 2D image planes, which limits its accuracy in 3D analysis. This paper presents a completely automated pipeline for generating patient-specific 3D biventricular heart models from cine magnetic resonance (MR) slices. Our pipeline automatically selects the relevant cine MR images, segments them using a deep learning-based method to extract the heart contours, and aligns the contours in 3D space correcting possible misalignments due to breathing or subject motion first using the intensity and contours information from the cine data and next with the help of a statistical shape model. Finally, the sparse 3D representation of the contours is used to generate a smooth 3D biventricular mesh. The computational pipeline is applied and evaluated in a CMR dataset of 20 healthy subjects. Our results show an average reduction of misalignment artefacts from 1.82 ± 1.60 mm to 0.72 ± 0.73 mm over 20 subjects, in terms of distance from the final reconstructed mesh. The high-resolution 3D biventricular meshes obtained with our computational pipeline are used for simulations of electrical activation patterns, showing agreement with non-invasive electrocardiographic imaging. The automatic methodologies presented here for patient-specific MR imaging-based 3D biventricular representations contribute to the efficient realization of precision medicine, enabling the enhanced interpretability of clinical data, the digital twin vision through patient-specific image-based modelling and simulation, and augmented reality applications. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: Heart auscultation is an inexpensive and fundamental technique to effectively diagnose cardiovascular disease. However, due to relatively high human error rates even when auscultation is performed by an experienced physician, and due to the not universal availability of qualified personnel, e.g. in developing countries, many efforts are made worldwide to propose computational tools for detecting abnormalities in heart sounds. The large heterogeneity of achievable data quality and devices, the variety of possible heart pathologies, and a generally poor signal-to-noise ratio make this problem very challenging. We present an accurate classification strategy for diagnosing heart sounds based on (1) automatic heart phase segmentation, (2) state-of-the art filters drawn from the field of speech synthesis (mel-frequency cepstral representation) and (3) an ad hoc multi-branch, multi-instance artificial neural network based on convolutional layers and fully connected neuronal ensembles which separately learns from each heart phase hence implicitly leveraging their different physiological significance. We demonstrate that it is possible to train our architecture to reach very high performances, e.g. an area under the curve of 0.87 or a sensitivity of 0.97. Our machine-learning-based tool could be employed for heartsound classification, especially as a screening tool in a variety of situations including telemedicine applications. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: The study of functional brain–heart interplay has provided meaningful insights in cardiology and neuroscience. Regarding biosignal processing, this interplay involves predominantly neural and heartbeat linear dynamics expressed via time and frequency domain-related features. However, the dynamics of central and autonomous nervous systems show nonlinear and multifractal behaviours, and the extent to which this behaviour influences brain–heart interactions is currently unknown. Here, we report a novel signal processing framework aimed at quantifying nonlinear functional brain–heart interplay in the non-Gaussian and multifractal domains that combines electroencephalography (EEG) and heart rate variability series. This framework relies on a maximal information coefficient analysis between nonlinear multiscale features derived from EEG spectra and from an inhomogeneous point-process model for heartbeat dynamics. Experimental results were gathered from 24 healthy volunteers during a resting state and a cold pressor test, revealing that synchronous changes between brain and heartbeat multifractal spectra occur at higher EEG frequency bands and through nonlinear/complex cardiovascular control. We conclude that significant bodily, sympathovagal changes such as those elicited by cold-pressure stimuli affect the functional brain–heart interplay beyond second-order statistics, thus extending it to multifractal dynamics. These results provide a platform to define novel nervous-system-targeted biomarkers. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: A massive amount of multimodal data are continuously collected in the intensive care unit (ICU) along each patient stay, offering a great opportunity for the development of smart monitoring devices based on artificial intelligence (AI). The two main sources of relevant information collected in the ICU are the electronic health records (EHRs) and vital sign waveforms continuously recorded at the bedside. While EHRs are already widely processed by AI algorithms for prompt diagnosis and prognosis, AI-based assessments of the patients’ pathophysiological state using waveforms are less developed, and their use is still limited to real-time monitoring for basic visual vital sign feedback at the bedside. This study uses data from the MIMIC-III database (PhysioNet) to propose a novel AI approach in ICU patient monitoring that incorporates features estimated by a closed-loop cardiovascular model, with the specific goal of identifying sepsis within the first hour of admission. Our top benchmark results (AUROC = 0.92, AUPRC = 0.90) suggest that features derived by cardiovascular control models may play a key role in identifying sepsis, by continuous monitoring performed through advanced multivariate modelling of vital sign waveforms. This work lays foundations for a deeper data integration paradigm which will help clinicians in their decision-making processes. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: The dynamic interplay between central and autonomic nervous system activities plays a pivotal role in orchestrating sleep. Macrostructural changes such as sleep-stage transitions or phasic, brief cortical events elicit fluctuations in neural outflow to the cardiovascular system, but the causal relationships between cortical and cardiovascular activities underpinning the microstructure of sleep are largely unknown. Here, we investigate cortical–cardiovascular interactions during the cyclic alternating pattern (CAP) of non-rapid eye movement sleep in a diverse set of overnight polysomnograms. We determine the Granger causality in both 507 CAP and 507 matched non-CAP sequences to assess the causal relationships between electroencephalography (EEG) frequency bands and respiratory and cardiovascular variables (heart period, respiratory period, pulse arrival time and pulse wave amplitude) during CAP. We observe a significantly stronger influence of delta activity on vascular variables during CAP sequences where slow, low-amplitude EEG activation phases (A1) dominate than during non-CAP sequences. We also show that rapid, high-amplitude EEG activation phases (A3) provoke a more pronounced change in autonomic activity than A1 and A2 phases. Our analysis provides the first evidence on the causal interplay between cortical and cardiovascular activities during CAP. Granger causality analysis may also be useful for probing the level of decoupling in sleep disorders. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: We propose a procedure suitable for automated synchrogram analysis for setting the threshold below which phase variability between two marker event series is of such a negligible amount that the null hypothesis of phase desynchronization can be rejected. The procedure exploits the principle of maximizing the likelihood of detecting phase synchronization epochs and it is grounded on a surrogate data approach testing the null hypothesis of phase uncoupling. The approach was applied to assess cardiorespiratory phase interactions between heartbeat and inspiratory onset in amateur cyclists before and after 11-week inspiratory muscle training (IMT) at different intensities and compared to a more traditional approach to set phase variability threshold. The proposed procedure was able to detect the decrease in cardiorespiratory phase locking strength during vagal withdrawal induced by the modification of posture from supine to standing. IMT had very limited effects on cardiorespiratory phase synchronization strength and this result held regardless of the training intensity. In amateur athletes training, the inspiratory muscles did not limit the decrease in cardiorespiratory phase synchronization observed in the upright position as a likely consequence of the modest impact of this respiratory exercise, regardless of its intensity, on cardiac vagal control. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

Description: Recent advancements in detrended fluctuation analysis (DFA) allow evaluating multifractal coefficients scale-by-scale, a promising approach for assessing the complexity of biomedical signals. The multifractality degree is typically quantified by the singularity spectrum width ( W SS ), a method that is critically unstable in multiscale applications. Thus, we aim to propose a robust multiscale index of multifractality, compare it with W SS and illustrate its performance on real biosignals. The proposed index is the cumulative function of squared increments between consecutive DFA coefficients at each scale n : α CF ( n ). We compared it with W SS calculated scale-by-scale considering monofractal/monoscale, monofractal/multiscale, multifractal/monoscale and multifractal/multiscale random processes. The two indices provided qualitatively similar descriptions of multifractality, but α CF ( n ) differentiated better the multifractal components from artefacts due to crossovers or detrending overfitting. Applied on 24 h heart rate recordings of 14 participants, the singularity spectrum failed to always satisfy the concavity requirement for providing meaningful W SS , while α CF ( n ) demonstrated a statistically significant heart rate multifractality at night in the scale ranges 16–100 and 256–680 s. Furthermore, α CF ( n ) did not reject the hypothesis of monofractality at daytime, coherently with previous reports of lower nonlinearity and monoscale multifractality during the day. Thus, α CF ( n ) appears a robust index of multiscale multifractality that is useful for quantifying complexity alterations of physiological series. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.

Description: Recent studies have suggested that cardiac abnormalities can be detected from the electrocardiogram (ECG) using deep machine learning (DL) models. However, most DL algorithms lack interpretability, since they do not provide any justification for their decisions. In this study, we designed two new frameworks to interpret the classification results of DL algorithms trained for 12-lead ECG classification. The frameworks allow us to highlight not only the ECG samples that contributed most to the classification, but also which between the P-wave, QRS complex and T-wave, hereafter simply called ‘waves’, were the most relevant for the diagnosis. The frameworks were designed to be compatible with any DL model, including the ones already trained. The frameworks were tested on a selected Deep Neural Network, trained on a publicly available dataset, to automatically classify 24 cardiac abnormalities from 12-lead ECG signals. Experimental results showed that the frameworks were able to detect the most relevant ECG waves contributing to the classification. Often the network relied on portions of the ECG which are also considered by cardiologists to detect the same cardiac abnormalities, but this was not always the case. In conclusion, the proposed frameworks may unveil whether the network relies on features which are clinically significant for the detection of cardiac abnormalities from 12-lead ECG signals, thus increasing the trust in the DL models. This article is part of the theme issue ‘Advanced computation in cardiovascular physiology: new challenges and opportunities’.