Search

A three-dimensional dynamic model of the electrical activity of the heart is presented. The model is based on the single dipole model of the heart and is later related to the body surface potentials through a linear model which accounts for the temporal movements and rotations of the cardiac dipole, together with a realistic ECG noise model. The proposed model is also generalized to maternal and fetal ECG mixtures recorded from the abdomen of pregnant women in single and multiple pregnancies. The applicability of the model for the evaluation of signal processing algorithms is illustrated using independent component analysis. Considering the difficulties and limitations of recording long-term ECG data, especially from pregnant women, the model described in this paper may serve as an effective means of simulation and analysis of a wide range of ECGs, including adults and fetuses.

Understanding sleep stages is crucial for diagnosing sleep disorders, developing treatments, and studying sleep's impact on overall health. With the growing availability of affordable brain monitoring devices, the volume of collected brain data has increased significantly. However, analyzing these data, particularly when using the gold standard multi-lead electroencephalogram (EEG), remains resource-intensive and time-consuming. To address this challenge, automated brain monitoring has emerged as a crucial solution for cost-effective and efficient EEG data analysis. A critical component of sleep analysis is detecting transitions between wakefulness and sleep states. These transitions offer valuable insights into sleep quality and quantity, essential for diagnosing sleep disorders, designing effective interventions, enhancing overall health and well-being, and studying sleep's effects on cognitive function, mood, and physical performance. This study presents a novel EEG feature extraction pipeline for the accurate classification of various wake and sleep stages. We propose a noise-robust model-based Kalman filtering (KF) approach to track changes in a time-varying auto-regressive model (TVAR) applied to EEG data during different wake and sleep stages. Our approach involves extracting features, including instantaneous frequency and instantaneous power from EEG, and implementing a two-step classifier for sleep staging. The first step classifies data into wake, REM, and non-REM categories, while the second step further classifies non-REM data into N1, N2, and N3 stages. Evaluation on the extended Sleep-EDF dataset (Sleep-EDFx), with 153 EEG recordings from 78 subjects, demonstrated compelling results with classifiers including Logistic Regression, Support Vector Machines, Extreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LGBM). The best performance was achieved with the LGBM and XGBoost classifiers, yielding an overall accuracy of over 77%, a macro-averaged F1 score of 0.69, and a Cohen's kappa of 0.68, highlighting the efficacy of the proposed method with a remarkably compact and interpretable feature set.

Hypertensive disorders of pregnancy (HDPs) remain a major challenge in maternal health. Early prediction of HDPs is crucial for timely intervention. Most existing predictive machine learning (ML) models rely on costly methods like blood, urine, genetic tests, and ultrasound, often extracting features from data gathered throughout pregnancy, delaying intervention. This study developed an ML model to identify HDP risk before clinical onset using affordable methods. Features were extracted from blood pressure (BP) measurements, body mass index values (BMI) recorded during the first and second trimesters, and maternal demographic information. We employed a random forest classification model for its robustness and ability to handle complex datasets. Our dataset, gathered from large academic medical centers in Atlanta, Georgia, United States (2010-2022), comprised 1,190 patients with 1,216 records collected during the first and second trimesters. Despite the limited number of features, the model's performance demonstrated a strong ability to accurately predict HDPs. The model achieved an F1-score, accuracy, positive predictive value, and area under the receiver-operating characteristic curve of 0.76, 0.72, 0.75, and 0.78, respectively. In conclusion, the model was shown to be effective in capturing the relevant patterns in the feature set necessary for predicting HDPs. Moreover, it can be implemented using simple devices, such as BP monitors and weight scales, providing a practical solution for early HDPs prediction in low-resource settings with proper testing and validation. By improving the early detection of HDPs, this approach can potentially help with the management of adverse pregnancy outcomes.

We introduce the ECG-Image-Database, a large and diverse collection of electrocardiogram (ECG) images generated from ECG time-series data, with real-world scanning, imaging, and physical artifacts. We used ECG-Image-Kit, an open-source Python toolkit, to generate realistic images of 12-lead ECG printouts from raw ECG time-series. The images include realistic distortions such as noise, wrinkles, stains, and perspective shifts, generated both digitally and physically. The toolkit was applied to 977 12-lead ECG records from the PTB-XL database and 1,000 from Emory Healthcare to create high-fidelity synthetic ECG images. These unique images were subjected to both programmatic distortions using ECG-Image-Kit and physical effects like soaking, staining, and mold growth, followed by scanning and photography under various lighting conditions to create real-world artifacts. The resulting dataset includes 35,595 software-labeled ECG images with a wide range of imaging artifacts and distortions. The dataset provides ground truth time-series data alongside the images, offering a reference for developing machine and deep learning models for ECG digitization and classification. The images vary in quality, from clear scans of clean papers to noisy photographs of degraded papers, enabling the development of more generalizable digitization algorithms. ECG-Image-Database addresses a critical need for digitizing paper-based and non-digital ECGs for computerized analysis, providing a foundation for developing robust machine and deep learning models capable of converting ECG images into time-series. The dataset aims to serve as a reference for ECG digitization and computerized annotation efforts. ECG-Image-Database was used in the PhysioNet Challenge 2024 on ECG image digitization and classification.

Introduction: Undetected high-risk conditions in pregnancy are a leading cause of perinatal mortality in low-income and middle-income countries. A key contributor to adverse perinatal outcomes in these settings is limited access to high-quality screening and timely referral to care. Recently, a low-cost one-dimensional Doppler ultrasound (1-D DUS) device was developed that front-line workers in rural Guatemala used to collect quality maternal and fetal data. Further, we demonstrated with retrospective preliminary data that 1-D DUS signal could be processed using artificial intelligence and deep-learning algorithms to accurately estimate fetal gestational age, intrauterine growth and maternal blood pressure. This protocol describes a prospective observational pregnancy cohort study designed to prospectively evaluate these preliminary findings., Methods and Analysis: This is a prospective observational cohort study conducted in rural Guatemala. In this study, we will follow pregnant women (N =700) recruited prior to 18 6/7 weeks gestation until their delivery and early postpartum period. During pregnancy, trained nurses will collect data on prenatal risk factors and obstetrical care. Every 4 weeks, the research team will collect maternal weight, blood pressure and 1-D DUS recordings of fetal heart tones. Additionally, we will conduct three serial obstetric ultrasounds to evaluate for fetal growth restriction (FGR), and one postpartum visit to record maternal blood pressure and neonatal weight and length. We will compare the test characteristics (receiver operator curves) of 1-D DUS algorithms developed by deep-learning methods to two-dimensional fetal ultrasound survey and published clinical pre-eclampsia risk prediction algorithms for predicting FGR and pre-eclampsia, respectively., Ethics and Dissemination: Results of this study will be disseminated at scientific conferences and through peer-reviewed articles. Deidentified data sets will be made available through public repositories. The study has been approved by the institutional ethics committees of Maya Health Alliance and Emory University., Competing Interests: Competing interests: The bespoke Android App, source code and algorithms developed for this study are open source and will be available through appropriate public repositories on project completion. The authors have no financial interest in the app or source code. PR and GDC receive funding from the Google Nonprofit Foundation for other artificial intelligence projects related to detection of maternal and neonatal conditions in low-resource settings., (© Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Background: Atrial fibrillation (AFib) detection via mobile ECG devices is promising, but algorithms often struggle to generalize across diverse datasets and platforms, limiting their real-world applicability. Objective: This study aims to develop a robust, generalizable AFib detection approach for mobile ECG devices using crowdsourced algorithms. Methods: We developed a voting algorithm using random forest, integrating six open-source AFib detection algorithms from the PhysioNet Challenge. The algorithm was trained on an AliveCor dataset and tested on two disjoint AliveCor datasets and one Apple Watch dataset. Results: The voting algorithm outperformed the base algorithms across all metrics: the average of sensitivity (0.884), specificity (0.988), PPV (0.917), NPV (0.985), and F1-score (0.943) on all datasets. It also demonstrated the least variability among datasets, signifying its highest robustness and effectiveness in diverse data environments. Moreover, it surpassed Apple's algorithm on all metrics and showed higher specificity but lower sensitivity than AliveCor's Kardia algorithm. Conclusions: This study demonstrates the potential of crowdsourced, multi-algorithmic strategies in enhancing AFib detection. Our approach shows robust cross-platform performance, addressing key generalization challenges in AI-enabled cardiac monitoring and underlining the potential for collaborative algorithms in wearable monitoring devices.

Background: Atrial fibrillation (AF) is often asymptomatic and thus under-observed. Given the high risks of stroke and heart failure among patients with AF, early prediction and effective management are crucial. Given the prevalence of obstructive sleep apnea among AF patients, electrocardiogram (ECG) analysis from polysomnography (PSG) offers a unique opportunity for early AF prediction. Our aim is to identify individuals at high risk of AF development from single‑lead ECGs during standard PSG., Methods: We analyzed 18,782 single‑lead ECG recordings from 13,609 subjects undergoing PSG at the Massachusetts General Hospital sleep laboratory. AF presence was identified using ICD-9/10 codes. The dataset included 15,913 recordings without AF history and 2054 recordings from patients diagnosed with AF between one month to fifteen years post-PSG. Data were partitioned into training, validation, and test cohorts ensuring that individual patients remained exclusive to each cohort. The test set was held out during the training process. We employed two different methods for feature extraction to build a final model for AF prediction: Extraction of hand-crafted ECG features and a deep learning method. For extraction of ECG-hand-crafted features, recordings were split into 30-s windows, and those with a signal quality index (SQI) below 0.95 were discarded. From each remaining window, 150 features were extracted from the time, frequency, time-frequency domains, and phase-space reconstructions of the ECG. A compilation of 12 statistical features summarized these window-specific features per recording, resulting in 1800 features (12 × 150). A pre-trained deep neural network from the PhysioNet Challenge 2021 was updated using transfer learning to discriminate recordings with and without AF. The model processed PSG ECGs in 16-s windows to generate AF probabilities, from which 13 statistical features were extracted. Combining 1800 features from feature extraction with 13 from the deep learning model, we performed a feature selection and subsequently trained a shallow neural network to predict future AF and evaluated its performance on the test cohort., Results: On the test set, our model exhibited sensitivity, specificity, and precision of 0.67, 0.81, and 0.3, respectively, for AF prediction. Survival analysis revealed a hazard ratio of 8.36 (p-value: 1.93 × 10 -52 ) for AF outcomes using the log-rank test., Conclusions: Our proposed ECG analysis method, utilizing overnight PSG data, shows promise in AF prediction despite modest precision, suggesting false positives. This approach could enable low-cost screening and proactive treatment for high-risk patients. Refinements, including additional physiological parameters, may reduce false positives, enhancing clinical utility and accuracy., Competing Interests: Declaration of competing interest None., (Copyright © 2024. Published by Elsevier Inc.)

Tremor, defined as an "involuntary, rhythmic, oscillatory movement of a body part", is a key feature of many neurological conditions including Parkinson's disease and essential tremor. Clinical assessment continues to be performed by visual observation with quantification on clinical scales. Methodologies for objectively quantifying tremor are promising but remain non-standardized across centers. Our center performs full-body behavioral testing with 3D motion capture for clinical and research purposes in patients with Parkinson's disease, essential tremor, and other conditions. The objective of this study was to assess the ability of several candidate processing pipelines to identify the presence or absence of tremor in kinematic data from patients with confirmed movement disorders and compare them to expert ratings from movement disorders specialists. We curated a database of 2272 separate kinematic data recordings from our center, each of which was contemporaneously annotated as tremor present or absent by a movement physician. We compared the ability of six separate processing pipelines to recreate clinician ratings based on F1 score, in addition to accuracy, precision, and recall. The performance across algorithms was generally comparable. The average F1 score was 0.84±0.02 (mean ± SD; range 0.81-0.87). The second highest performing algorithm (cross-validated F1=0.87) was a hybrid that used engineered features adapted from an algorithm in longstanding clinical use with a modern Support Vector Machine classifier. Taken together, our results suggest the potential to update legacy clinical decision support systems to incorporate modern machine learning classifiers to create better-performing tools.

Objective. Cardiovascular diseases are a major cause of mortality globally, and electrocardiograms (ECGs) are crucial for diagnosing them. Traditionally, ECGs are stored in printed formats. However, these printouts, even when scanned, are incompatible with advanced ECG diagnosis software that require time-series data. Digitizing ECG images is vital for training machine learning models in ECG diagnosis, leveraging the extensive global archives collected over decades. Deep learning models for image processing are promising in this regard, although the lack of clinical ECG archives with reference time-series data is challenging. Data augmentation techniques using realistic generative data models provide a solution. Approach. We introduce ECG-Image-Kit , an open-source toolbox for generating synthetic multi-lead ECG images with realistic artifacts from time-series data, aimed at automating the conversion of scanned ECG images to ECG data points. The tool synthesizes ECG images from real time-series data, applying distortions like text artifacts, wrinkles, and creases on a standard ECG paper background. Main results. As a case study, we used ECG-Image-Kit to create a dataset of 21 801 ECG images from the PhysioNet QT database. We developed and trained a combination of a traditional computer vision and deep neural network model on this dataset to convert synthetic images into time-series data for evaluation. We assessed digitization quality by calculating the signal-to-noise ratio and compared clinical parameters like QRS width, RR, and QT intervals recovered from this pipeline, with the ground truth extracted from ECG time-series. The results show that this deep learning pipeline accurately digitizes paper ECGs, maintaining clinical parameters, and highlights a generative approach to digitization. Significance. The toolbox has broad applications, including model development for ECG image digitization and classification. The toolbox currently supports data augmentation for the 2024 PhysioNet Challenge, focusing on digitizing and classifying paper ECG images., (Creative Commons Attribution license.)

Objective. The EPHNOGRAM project aimed to develop a low-cost, low-power device for simultaneous electrocardiogram (ECG) and phonocardiogram (PCG) recording, with additional channels for environmental audio to enhance PCG through active noise cancellation. The objective was to study multimodal electro-mechanical activities of the heart, offering insights into the differences and synergies between these modalities during various cardiac activity levels. Approach. We developed and tested several hardware prototypes of a simultaneous ECG-PCG acquisition device. Using this technology, we collected simultaneous ECG and PCG data from 24 healthy adults during different physical activities, including resting, walking, running, and stationary biking, in an indoor fitness center. The data were annotated using a robust software that we developed for detecting ECG R-peaks and PCG S1 and S2 components, and overseen by a human expert. We also developed machine learning models using ECG-based, PCG-based, and joint ECG-PCG features, like R-R and S1-S2 intervals, to classify physical activities and analyze electro-mechanical dynamics. Main results. The results show a significant coupling between ECG and PCG components, especially during high-intensity exercise. Notable micro-variations in S2-based heart rate show differences in the heart's electrical and mechanical functions. The Lomb-Scargle periodogram and approximate entropy analyses confirm the higher volatility of S2-based heart rate compared to ECG-based heart rate. Correlation analysis shows stronger coupling between R-R and R-S1 intervals during high-intensity activities. Hybrid ECG-PCG features, like the R-S2 interval, were identified as more informative for physical activity classification through mRMR feature selection and SHAP value analysis. Significance. The EPHNOGRAM database, is available on PhysioNet. The database enhances our understanding of cardiac function, enabling future studies on the heart's mechanical and electrical interrelationships. The results of this study can contribute to improved cardiac condition diagnoses. Additionally, the designed hardware has the potential for integration into wearable devices and the development of multimodal stress test technologies., (Creative Commons Attribution license.)

Regular blood pressure (BP) monitoring in clinical and ambulatory settings plays a crucial role in the prevention, diagnosis, treatment, and management of cardiovascular diseases. Recently, the widespread adoption of ambulatory BP measurement devices has been predominantly driven by the increased prevalence of hypertension and its associated risks and clinical conditions. Recent guidelines advocate for regular BP monitoring as part of regular clinical visits or even at home. This increased utilization of BP measurement technologies has raised significant concerns regarding the accuracy of reported BP values across settings. In this survey, which focuses mainly on cuff-based BP monitoring technologies, we highlight how BP measurements can demonstrate substantial biases and variances due to factors such as measurement and device errors, demographics, and body habitus. With these inherent biases, the development of a new generation of cuff-based BP devices that use artificial intelligence (AI) has significant potential. We present future avenues where AI-assisted technologies can leverage the extensive clinical literature on BP-related studies together with the large collections of BP records available in electronic health records. These resources can be combined with machine learning approaches, including deep learning and Bayesian inference, to remove BP measurement biases and provide individualized BP-related cardiovascular risk indexes.

Background: Seizure detection is challenging outside the clinical environment due to the lack of comfortable, reliable, and practical long-term neurophysiological monitoring devices. We developed a novel, discreet, unobstructive in-ear sensing system that enables long-term electroencephalography (EEG) recording. This is the first study we are aware of that systematically compares the seizure detection utility of in-ear EEG with that of simultaneously recorded intracranial EEG. In addition, we present a similar comparison between simultaneously recorded in-ear EEG and scalp EEG., Methods: In this foundational research, we conducted a clinical feasibility study and validated the ability of the ear-EEG system to capture focal-onset seizures against 1255 hrs of simultaneous ear-EEG data along with scalp or intracranial EEG in 20 patients with refractory focal epilepsy (11 with scalp EEG, 8 with intracranial EEG, and 1 with both)., Results: In a blinded, independent review of the ear-EEG signals, two epileptologists were able to detect 86.4% of the seizures that were subsequently identified using the clinical gold standard EEG modalities, with a false detection rate of 0.1 per day, well below what has been reported for ambulatory monitoring. The few seizures not detected on the ear-EEG signals emanated from deep within the mesial temporal lobe or extra-temporally and remained very focal, without significant propagation. Following multiple sessions of recording for a median continuous wear time of 13 hrs, patients reported a high degree of tolerance for the device, with only minor adverse events reported by the scalp EEG cohort., Conclusions: These preliminary results demonstrate the potential of using ear-EEG to enable routine collection of complementary, prolonged, and remote neurophysiological evidence, which may permit real-time detection of paroxysmal events such as seizures and epileptiform discharges. This study suggests that the ear-EEG device may assist clinicians in making an epilepsy diagnosis, assessing treatment efficacy, and optimizing medication titration., (© 2024. The Author(s).)

Objectives: To develop the International Cardiac Arrest Research (I-CARE), a harmonized multicenter clinical and electroencephalography database for acute hypoxic-ischemic brain injury research involving patients with cardiac arrest., Design: Multicenter cohort, partly prospective and partly retrospective., Setting: Seven academic or teaching hospitals from the United States and Europe., Patients: Individuals 16 years old or older who were comatose after return of spontaneous circulation following a cardiac arrest who had continuous electroencephalography monitoring were included., Interventions: Not applicable., Measurements and Main Results: Clinical and electroencephalography data were harmonized and stored in a common Waveform Database-compatible format. Automated spike frequency, background continuity, and artifact detection on electroencephalography were calculated with 10-second resolution and summarized hourly. Neurologic outcome was determined at 3-6 months using the best Cerebral Performance Category (CPC) scale. This database includes clinical data and 56,676 hours (3.9 terabytes) of continuous electroencephalography data for 1,020 patients. Most patients died ( n = 603, 59%), 48 (5%) had severe neurologic disability (CPC 3 or 4), and 369 (36%) had good functional recovery (CPC 1-2). There is significant variability in mean electroencephalography recording duration depending on the neurologic outcome (range, 53-102 hr for CPC 1 and CPC 4, respectively). Epileptiform activity averaging 1 Hz or more in frequency for at least 1 hour was seen in 258 patients (25%) (19% for CPC 1-2 and 29% for CPC 3-5). Burst suppression was observed for at least 1 hour in 207 (56%) and 635 (97%) patients with CPC 1-2 and CPC 3-5, respectively., Conclusions: The I-CARE consortium electroencephalography database provides a comprehensive real-world clinical and electroencephalography dataset for neurophysiology research of comatose patients after cardiac arrest. This dataset covers the spectrum of abnormal electroencephalography patterns after cardiac arrest, including epileptiform patterns and those in the ictal-interictal continuum., Competing Interests: Dr. van Putten is the founder of Clinical Science Systems. Dr. Westover is a co-founder of Beacon Biosignals. The remaining authors have disclosed that they do not have any potential conflicts of interest., (Copyright © 2023 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved.)

Introduction: International Classification of Diseases (ICD) codes recorded in administrative data are often used to identify congenital heart defects (CHD). However, these codes may inaccurately identify true positive (TP) CHD individuals. CHD surveillance could be strengthened by accurate CHD identification in administrative records using machine learning (ML) algorithms., Methods: To identify features relevant to accurate CHD identification, traditional ML models were applied to a validated dataset of 779 patients; encounter level data, including ICD-9-CM and CPT codes, from 2011 to 2013 at four US sites were utilized. Five-fold cross-validation determined overlapping important features that best predicted TP CHD individuals. Median values and 95% confidence intervals (CIs) of area under the receiver operating curve, positive predictive value (PPV), negative predictive value, sensitivity, specificity, and F1-score were compared across four ML models: Logistic Regression, Gaussian Naive Bayes, Random Forest, and eXtreme Gradient Boosting (XGBoost)., Results: Baseline PPV was 76.5% from expert clinician validation of ICD-9-CM CHD-related codes. Feature selection for ML decreased 7138 features to 10 that best predicted TP CHD cases. During training and testing, XGBoost performed the best in median accuracy (F1-score) and PPV, 0.84 (95% CI: 0.76, 0.91) and 0.94 (95% CI: 0.91, 0.96), respectively. When applied to the entire dataset, XGBoost revealed a median PPV of 0.94 (95% CI: 0.94, 0.95)., Conclusions: Applying ML algorithms improved the accuracy of identifying TP CHD cases in comparison to ICD codes alone. Use of this technique to identify CHD cases would improve generalizability of results obtained from large datasets to the CHD patient population, enhancing public health surveillance efforts., (© 2023 Wiley Periodicals LLC.)

Cardiac auscultation is an accessible diagnostic screening tool that can help to identify patients with heart murmurs, who may need follow-up diagnostic screening and treatment for abnormal cardiac function. However, experts are needed to interpret the heart sounds, limiting the accessibility of cardiac auscultation in resource-constrained environments. Therefore, the George B. Moody PhysioNet Challenge 2022 invited teams to develop algorithmic approaches for detecting heart murmurs and abnormal cardiac function from phonocardiogram (PCG) recordings of heart sounds. For the Challenge, we sourced 5272 PCG recordings from 1452 primarily pediatric patients in rural Brazil, and we invited teams to implement diagnostic screening algorithms for detecting heart murmurs and abnormal cardiac function from the recordings. We required the participants to submit the complete training and inference code for their algorithms, improving the transparency, reproducibility, and utility of their work. We also devised an evaluation metric that considered the costs of screening, diagnosis, misdiagnosis, and treatment, allowing us to investigate the benefits of algorithmic diagnostic screening and facilitate the development of more clinically relevant algorithms. We received 779 algorithms from 87 teams during the Challenge, resulting in 53 working codebases for detecting heart murmurs and abnormal cardiac function from PCG recordings. These algorithms represent a diversity of approaches from both academia and industry, including methods that use more traditional machine learning techniques with engineered clinical and statistical features as well as methods that rely primarily on deep learning models to discover informative features. The use of heart sound recordings for identifying heart murmurs and abnormal cardiac function allowed us to explore the potential of algorithmic approaches for providing more accessible diagnostic screening in resource-constrained environments. The submission of working, open-source algorithms and the use of novel evaluation metrics supported the reproducibility, generalizability, and clinical relevance of the research from the Challenge., Competing Interests: I have read the journal’s policy and the authors of this manuscript have the following competing interests: AE receives financial support through grant PID2021-122727OB-I00 funded by MCIN/AEI/10.13039/501100011033 and "ERDF A way of making Europe" and by the Basque Government under Grant IT1717-22. FR and MC receive financial support by National Funds through the Portuguese funding agency, FCT - Fundação para a Ciência e a Tecnologia, within project UIDB/50014/2020. GC has financial interests in AliveCor, LifeBell AI and Mindchild Medical. GC also holds a board position in LifeBell AI and Mindchild Medical., (Copyright: © 2023 Reyna et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Objective: Murmurs are abnormal heart sounds, identified by experts through cardiac auscultation. The murmur grade, a quantitative measure of the murmur intensity, is strongly correlated with the patient's clinical condition. This work aims to estimate each patient's murmur grade (i.e., absent, soft, loud) from multiple auscultation location phonocardiograms (PCGs) of a large population of pediatric patients from a low-resource rural area., Methods: The Mel spectrogram representation of each PCG recording is given to an ensemble of 15 convolutional residual neural networks with channel-wise attention mechanisms to classify each PCG recording. The final murmur grade for each patient is derived based on the proposed decision rule and considering all estimated labels for available recordings. The proposed method is cross-validated on a dataset consisting of 3456 PCG recordings from 1007 patients using a stratified ten-fold cross-validation. Additionally, the method was tested on a hidden test set comprised of 1538 PCG recordings from 442 patients., Results: The overall cross-validation performances for patient-level murmur gradings are 86.3% and 81.6% in terms of the unweighted average of sensitivities and F1-scores, respectively. The sensitivities (and F1-scores) for absent, soft, and loud murmurs are 90.7% (93.6%), 75.8% (66.8%), and 92.3% (84.2%), respectively. On the test set, the algorithm achieves an unweighted average of sensitivities of 80.4% and an F1-score of 75.8%., Conclusions: This study provides a potential approach for algorithmic pre-screening in low-resource settings with relatively high expert screening costs., Significance: The proposed method represents a significant step beyond detection of murmurs, providing characterization of intensity, which may provide an enhanced classification of clinical outcomes.

Stethoscope-recorded chest sounds provide the opportunity for remote cardio-respiratory health monitoring of neonates. However, reliable monitoring requires high-quality heart and lung sounds. This paper presents novel artificial intelligence-based Non-negative Matrix Factorisation (NMF) and Non-negative Matrix Co-Factorisation (NMCF) methods for neonatal chest sound separation. To assess these methods and compare them with existing single-channel separation methods, an artificial mixture dataset was generated comprising heart, lung, and noise sounds. Signal-to-noise ratios were then calculated for these artificial mixtures. These methods were also tested on real-world noisy neonatal chest sounds and assessed based on vital sign estimation error, and a signal quality score of 1-5, developed in our previous works. Overall, both the proposed NMF and NMCF methods outperform the next best existing method by 2.7 dB to 11.6 dB for the artificial dataset, and 0.40 to 1.12 signal quality improvement for the real-world dataset. The median processing time for the sound separation of a 10 s recording was found to be 28.3 s for NMCF and 342 ms for NMF. With the stable and robust performance of our proposed methods, we believe these methods are useful to denoise neonatal heart and lung sounds in the real-world environment.

Assessing fetal development is essential to the provision of healthcare for both mothers and fetuses. In low- and middle-income countries, conditions that increase the risk of fetal growth restriction (FGR) are often more prevalent. In these regions, barriers to accessing healthcare and social services exacerbate fetal maternal health problems. One of these barriers is the lack of affordable diagnostic technologies. To address this issue, this work introduces an end-to-end algorithm applied to a low-cost, hand-held Doppler ultrasound device for estimating gestational age (GA), and by inference, FGR. The Doppler ultrasound signals used in this study were collected from 226 pregnancies (45 low birth weight at delivery) between 5 and 9 months GA by lay midwives in highland Guatemala. We designed a hierarchical deep sequence learning model with an attention mechanism to learn the normative dynamics of fetal cardiac activity in different stages of development. This resulted in a state-of-the-art GA estimation performance, with an average error of 0.79 months. This is close to the theoretical minimum for the given quantization level of one month. The model was then tested on Doppler recordings of the fetuses with low birth weight and the estimated GA was shown to be lower than the GA calculated from last menstruation. Thus, this could be interpreted as a potential sign of developmental retardation (or FGR) associated with low birth weight, and referral and intervention may be necessary.

Objectives. People with refractory epilepsy are overwhelmed by the uncertainty of their next seizures. Accurate prediction of future seizures could greatly improve the quality of life for these patients. New evidence suggests that seizure occurrences can have cyclical patterns for some patients. Even though these cyclicalities are not intuitive, they can be identified by machine learning (ML), to identify patients with predictable vs unpredictable seizure patterns. Approach. Self-reported seizure logs of 153 patients from the Human Epilepsy Project with more than three reported seizures (totaling 8337 seizures) were used to obtain inter-seizure interval time-series for training and evaluation of the forecasting models. Two classes of prediction methods were studied: (1) statistical approaches using Bayesian fusion of population-wise and individual-wise seizure patterns; and (2) ML-based algorithms including least squares, least absolute shrinkage and selection operator, support vector machine (SVM) regression, and long short-term memory regression. Leave-one-person-out cross-validation was used for training and evaluation, by training on seizure diaries of all except one subject and testing on the left-out subject. Main results. The leading forecasting models were the SVM regression and a statistical model that combined the median of population-wise seizure time-intervals with a test subject's prior seizure intervals. SVM was able to forecast 50%, 70%, 81%, 84%, and 87% of seizures of unseen subjects within 0, 1, 2, 3 to 4 d of mean absolute forecasting error, respectively. The subject-wise performances show that patients with more frequent seizures were generally better predicted. Significance. ML models can leverage non-random patterns within self-reported seizure diaries to forecast future seizures. While diary-based seizure forecasting alone is only one of many aspects of clinical care of patients with epilepsy, studying the level of predictability across seizures and patients paves the path towards a better understanding of predictable vs unpredictable seizures on individualized and population-wise bases., (© 2022 Institute of Physics and Engineering in Medicine.)

Despite the recent explosion of machine learning applied to medical data, very few studies have examined algorithmic bias in any meaningful manner, comparing across algorithms, databases, and assessment metrics. In this study, we compared the biases in sex, age, and race of 56 algorithms on over 130,000 electrocardiograms (ECGs) using several metrics and propose a machine learning model design to reduce bias. Participants of the 2021 PhysioNet Challenge designed and implemented working, open-source algorithms to identify clinical diagnosis from 2- lead ECG recordings. We grouped the data from the training, validation, and test datasets by sex (male vs female), age (binned by decade), and race (Asian, Black, White, and Other) whenever possible. We computed recording-wise accuracy, area under the receiver operating characteristic curve (AUROC), area under the precision recall curve (AUPRC), F-measure, and the Challenge Score for each of the 56 algorithms. The Mann-Whitney U and the Kruskal-Wallis tests assessed the performance differences of algorithms across these demographic groups. Group trends revealed similar values for the AUROC, AUPRC, and F-measure for both male and female groups across the training, validation, and test sets. However, recording-wise accuracies were 20% higher (p < 0.01) and the Challenge Score 12% lower (p = 0.02) for female subjects on the test set. AUPRC, F-measure, and the Challenge Score increased with age, while recording-wise accuracy and AUROC decreased with age. The results were similar for the training and test sets, but only recording-wise accuracy (12% decrease per decade, p < 0.01), Challenge Score (1% increase per decade, p < 0.01), and AUROC (1% decrease per decade, p < 0.01) were statistically different on the test set. We observed similar AUROC, AUPRC, Challenge Score, and F-measure values across the different race categories. But, recording-wise accuracies were significantly lower for Black subjects and higher for Asian subjects on the training (31% difference, p < 0.01) and test (39% difference, p < 0.01) sets. A top performing model was then retrained using an additional constraint which simultaneously minimized differences in performance across sex, race and age. This resulted in a modest reduction in performance, with a significant reduction in bias. This work provides a demonstration that biases manifest as a function of model architecture, population, cost function and optimization metric, all of which should be closely examined in any model., Competing Interests: Declaration of Competing Interest None., (Copyright © 2022 Elsevier Inc. All rights reserved.)

Cardiac auscultation is one of the most cost-effective techniques used to detect and identify many heart conditions. Computer-assisted decision systems based on auscultation can support physicians in their decisions. Unfortunately, the application of such systems in clinical trials is still minimal since most of them only aim to detect the presence of extra or abnormal waves in the phonocardiogram signal, i.e., only a binary ground truth variable (normal vs abnormal) is provided. This is mainly due to the lack of large publicly available datasets, where a more detailed description of such abnormal waves (e.g., cardiac murmurs) exists. To pave the way to more effective research on healthcare recommendation systems based on auscultation, our team has prepared the currently largest pediatric heart sound dataset. A total of 5282 recordings have been collected from the four main auscultation locations of 1568 patients, in the process, 215780 heart sounds have been manually annotated. Furthermore, and for the first time, each cardiac murmur has been manually annotated by an expert annotator according to its timing, shape, pitch, grading, and quality. In addition, the auscultation locations where the murmur is present were identified as well as the auscultation location where the murmur is detected more intensively. Such detailed description for a relatively large number of heart sounds may pave the way for new machine learning algorithms with a real-world application for the detection and analysis of murmur waves for diagnostic purposes.

As we transition away from pandemic-induced isolation and social distancing, there is a need to estimate the risk of exposure in built environments. We propose a novel metric to quantify social distancing and the potential risk of exposure to airborne diseases in an indoor setting, which scales with distance and the number of people present. The risk of exposure metric is designed to incorporate the dynamics of particle movement in an enclosed set of rooms for people at different immunity levels, susceptibility due to age, background infection rates, intrinsic individual risk factors (e.g., comorbidities), mask-wearing levels, the half-life of the virus and ventilation rate in the environment. The model parameters have been selected for COVID-19, although the modeling framework applies to other airborne diseases. The performance of the metric is tested using simulations of a real physical environment, combining models for walking, path length dynamics, and air-conditioning replacement action. We have also created a visualization tool to help identify high-risk areas in the built environment. The resulting software framework is being used to help with planning movement and scheduling in a clinical environment ahead of reopening of the facility, for deciding the maximum time within an environment that is safe for a given number of people, for air replacement settings on air-conditioning and heating systems, and for mask-wearing policies. The framework can also be used for identifying locations where foot traffic might create high-risk zones and for planning timetabled transitions of groups of people between activities in different spaces. Moreover, when coupled with individual-level location tracking (via radio-frequency tagging, for example), the exposure risk metric can be used in real-time to estimate the risk of exposure to the coronavirus or other airborne illnesses, and intervene through air-conditioning action modification, changes in timetabling of group activities, mask-wearing policies, or restricting the number of individuals entering a given room/space. All software are provided online under an open-source license.

Background: Atrial fibrillation (AFib) is the most common cardiac arrhythmia associated with stroke, blood clots, heart failure, coronary artery disease, and/or death. Multiple methods have been proposed for AFib detection, with varying performances, but no single approach appears to be optimal. We hypothesized that each state-of-the-art algorithm is appropriate for different subsets of patients and provides some independent information. Therefore, a set of suitably chosen algorithms, combined in a weighted voting framework, will provide a superior performance to any single algorithm., Methods: We investigate and modify 38 state-of-the-art AFib classification algorithms for a single-lead ambulatory electrocardiogram (ECG) monitoring device. All algorithms are ranked using a random forest classifier and an expert-labeled training dataset of 2,532 recordings. The seven top-ranked algorithms are combined by using an optimized weighting approach., Results: The proposed fusion algorithm, when validated on a separate test dataset consisting of 4,644 recordings, resulted in an area under the receiver operating characteristic (ROC) curve of 0.99. The sensitivity, specificity, positive-predictive-value (PPV), negative-predictive-value (NPV), and F1-score of the proposed algorithm were 0.93, 0.97, 0.87, 0.99, and 0.90, respectively, which were all superior to any single algorithm or any previously published., Conclusion: This study demonstrates how a set of well-chosen independent algorithms and a voting mechanism to fuse the outputs of the algorithms, outperforms any single state-of-the-art algorithm for AFib detection. The proposed framework is a case study for the general notion of crowdsourcing between open-source algorithms in healthcare applications. The extension of this framework to similar applications may significantly save time, effort, and resources, by combining readily existing algorithms. It is also a step toward the democratization of artificial intelligence and its application in healthcare., Competing Interests: I have read the journal’s policy and the authors of this manuscript have the following competing interests: D.A. is the Founder & Chief Medical Officer of AliveCor Inc. C.G, D.T., and J.X. are employees of AliveCor. G.C. is an advisor to AliveCor and holds significant stock. A.B.R., Q.L., and R.S. have no conflicts of interest. AliveCor provides unrestricted funds to Emory’s Department of Biomedical Informatics. This does not alter our adherence to PLOS ONE policies on sharing data and materials.

Common Spatial Pattern (CSP) is a popular feature extraction algorithm used for electroencephalogram (EEG) data classification in brain-computer interfaces. One of the critical operations used in CSP is taking the average of trial covariance matrices for each class. In this regard, the arithmetic mean, which minimizes the sum of squared Euclidean distances to the data points, is conventionally used; however, this operation ignores the Riemannian geometry in the manifold of covariance matrices. To alleviate this problem, Fréchet mean determined using different Riemannian distances have been used. In this paper, we are primarily concerned with the following question: Does using the Fréchet mean with Riemannian distances instead of arithmetic mean in averaging CSP covariance matrices improve the subject-independent classification of motor imagery (MI)? To answer this question we conduct a comparative study using the largest MI dataset to date, with 54 subjects and a total of 21,600 trials of left-and right-hand MI. The results indicate a general trend of having a statistically significant better performance when the Riemannian geometry is used.

Deep learning methods, and in particular Convolutional Neural Networks (CNNs), have shown breakthrough performance in a wide variety of classification applications, including electroencephalogram-based Brain Computer Interfaces (BCIs). Despite the advances in the field, BCIs are still far from the subject-independent decoding of brain activities, primarily due to substantial inter-subject variability. In this study, we examine the potential application of an ensemble CNN classifier to integrate the capabilities of CNN architectures and ensemble learning for decoding EEG signals collected in motor imagery experiments. The results prove the superiority of the proposed ensemble CNN in comparison with the average base CNN classifiers, with an improvement up to 9% in classification accuracy depending on the test subject. The results also show improvement with respect to the performance of a number of state-of-the-art methods that have been previously used for subject-independent classification in the same datasets used here (i.e., BCI Competition IV 2A and 2B datasets).

Non-invasive foetal electrocardiography (fECG) continues to be an open topic for research. The development of standard algorithms for the extraction of the fECG from the maternal electrophysiological interference is limited by the lack of publicly available reference datasets that could be used to benchmark different algorithms while providing a ground truth for foetal heart activity when an invasive scalp lead is unavailable. In this work, we present the Non-Invasive Multimodal Foetal ECG-Doppler Dataset for Antenatal Cardiology Research (NInFEA), the first open-access multimodal early-pregnancy dataset in the field that features simultaneous non-invasive electrophysiological recordings and foetal pulsed-wave Doppler (PWD). The dataset is mainly conceived for researchers working on fECG signal processing algorithms. The dataset includes 60 entries from 39 pregnant women, between the 21 st and 27 th week of gestation. Each dataset entry comprises 27 electrophysiological channels (2048 Hz, 22 bits), a maternal respiration signal, synchronised foetal trans-abdominal PWD and clinical annotations provided by expert clinicians during signal acquisition. MATLAB snippets for data processing are also provided.

Objective: Mixtures of temporally nonstationary signals are very common in biomedical applications. The nonstationarity of the source signals can be used as a discriminative property for signal separation. Herein, a semi-blind source separation algorithm is proposed for the extraction of temporally nonstationary components from linear multichannel mixtures of signals and noises., Methods: A hypothesis test is proposed for the detection and fusion of temporally nonstationary events, by using ad hoc indexes for monitoring the first and second order statistics of the innovation process. As proof of concept, the general framework is customized and tested over noninvasive fetal cardiac recordings acquired from the maternal abdomen, over publicly available datasets, using two types of nonstationarity detectors: 1) a local power variations detector, and 2) a model-deviations detector using the innovation process properties of an extended Kalman filter., Results: The performance of the proposed method is assessed in presence of white and colored noise, in different signal-to-noise ratios., Conclusion and Significance: The proposed scheme is general and it can be used for the extraction of nonstationary events and sample deviations from a presumed model in multivariate data, which is a recurrent problem in many machine learning applications.