arXiv subjects

Joachim A. Behar

Publications and source records attributed to Joachim A. Behar.

34 records · Page 2Linked to original sources

arXiv2023

Robust peak detection for photoplethysmography signal analysis

Efficient and accurate evaluation of long-term photoplethysmography (PPG) recordings is essential for both clinical assessments and consumer products. In 2021, the top opensource peak detectors were benchmarked on the Multi-Ethnic Study of Atherosclerosis (MESA) database consisting of polysomnography (PSG) recordings and continuous sleep PPG data, where the Automatic Beat Detector (Aboy) had the best accuracy. This work presents Aboy++, an improved version of the original Aboy beat detector. The algorithm was evaluated on 100 adult PPG recordings from the MESA database, which contains more than 4.25 million reference beats. Aboy++ achieved an F1-score of 85.5%, compared to 80.99% for the original Aboy peak detector. On average, Aboy++ processed a 1 hour-long recording in less than 2 seconds. This is compared to 115 seconds (i.e., over 57-times longer) for the open-source implementation of the original Aboy peak detector. This study demonstrated the importance of developing robust algorithms like Aboy++ to improve PPG data analysis and clinical outcomes. Overall, Aboy++ is a reliable tool for evaluating long-term wearable PPG measurements in clinical and consumer contexts.

physics.med-ph↗

arXiv2023

Machine Learning for Ranking f-wave Extraction Methods in Single-Lead ECGs

Introduction: The presence of fibrillatory waves (f-waves) is important in the diagnosis of atrial fibrillation (AF), which has motivated the development of methods for f-wave extraction. We propose a novel approach to benchmarking methods designed for single-lead ECG analysis, building on the hypothesis that better-performing AF classification using features computed from the extracted f-waves implies better-performing extraction. The approach is well-suited for processing large Holter data sets annotated with respect to the presence of AF. Methods: Three data sets with a total of 300 two- or three-lead Holter recordings, performed in the USA, Israel and Japan, were used as well as a simulated single-lead data set. Four existing extraction methods based on either average beat subtraction or principal component analysis (PCA) were evaluated. A random forest classifier was used for window-based AF classification. Performance was measured by the area under the receiver operating characteristic (AUROC). Results: The best performance was found for PCA-based extraction, resulting in AUROCs in the ranges 0.77--0.83, 0.62--0.78, and 0.87--0.89 for the data sets from USA, Israel, and Japan, respectively, when analyzed across leads; the AUROC of the simulated single-lead, noisy data set was 0.98. Conclusions: This study provides a novel approach to evaluating the performance of f-wave extraction methods, offering the advantage of not using ground truth f-waves for evaluation, thus being able to leverage real data sets for evaluation. The code is open source (following publication).

eess.SP↗

arXiv2023

FundusQ-Net: a Regression Quality Assessment Deep Learning Algorithm for Fundus Images Quality Grading

Objective: Ophthalmological pathologies such as glaucoma, diabetic retinopathy and age-related macular degeneration are major causes of blindness and vision impairment. There is a need for novel decision support tools that can simplify and speed up the diagnosis of these pathologies. A key step in this process is to automatically estimate the quality of the fundus images to make sure these are interpretable by a human operator or a machine learning model. We present a novel fundus image quality scale and deep learning (DL) model that can estimate fundus image quality relative to this new scale. Methods: A total of 1,245 images were graded for quality by two ophthalmologists within the range 1-10, with a resolution of 0.5. A DL regression model was trained for fundus image quality assessment. The architecture used was Inception-V3. The model was developed using a total of 89,947 images from 6 databases, of which 1,245 were labeled by the specialists and the remaining 88,702 images were used for pre-training and semi-supervised learning. The final DL model was evaluated on an internal test set (n=209) as well as an external test set (n=194). Results: The final DL model, denoted FundusQ-Net, achieved a mean absolute error of 0.61 (0.54-0.68) on the internal test set. When evaluated as a binary classification model on the public DRIMDB database as an external test set the model obtained an accuracy of 99%. Significance: the proposed algorithm provides a new robust tool for automated quality grading of fundus images.

eess.IV↗

arXiv2022

Estimation of f-wave Dominant Frequency Using a Voting Scheme

Introduction: Atrial fibrillation (AF) is the most common heart arrhythmia, characterized by the presence of fibrillatory waves (f-waves) in the ECG. We introduce a voting scheme to estimate the dominant atrial frequency (DAF) of f-waves. Methods: We analysed a subset of Holter recordings obtained from the University of Virginia AF Database. 100 Holter recordings with manually annotated AF events, resulting in a total 363 AF events lasting more than 1 min. The f-waves were extracted using four different template subtraction (TS) algorithms and the DAF was estimated from the first 1-min window of each AF event. A random forest classifier was used. We hypothesized that better extraction of the f-wave meant better AF/non-AF classification using the DAF as the single input feature of the RF model. Results: Performance on the test set, expressed in terms of AF/non-AF classification, was the best when the DAF was computed computed the three best-performing extraction methods. Using these three algorithms in a voting scheme, the classifier obtained AUC=0.60 and the DAFs were mostly spread around 6 Hz, 5.66 (4.83-7.47). Conclusions: This study has two novel contributions: (1) a method for assessing the performance of f-wave extraction algorithms, and (2) a voting scheme for improved DAF estimation.

eess.SP↗

arXiv2022

ArNet-ECG: Deep Learning for the Detection of Atrial Fibrillation from the Raw Electrocardiogram

Atrial fibrillation (AF) is the most prevalent heart arrhythmia. AF manifests on the electrocardiogram (ECG) though irregular beat-to-beat time interval variation, the absence of P-wave and the presence of fibrillatory waves (f-wave). We hypothesize that a deep learning (DL) approach trained on the raw ECG will enable robust detection of AF events and the estimation of the AF burden (AFB). We further hypothesize that the performance reached leveraging the raw ECG will be superior to previously developed methods using the beat-to-beat interval variation time series. Consequently, we develop a new DL algorithm, denoted ArNet-ECG, to robustly detect AF events and estimate the AFB from the raw ECG and benchmark this algorithms against previous work. Methods: A dataset including 2,247 adult patients and totaling over 53,753 hours of continuous ECG from the University of Virginia (UVAF) was used. Results: ArNet-ECG obtained an F1 of 0.96 and ArNet2 obtained an F1 0.94. Discussion and conclusion: ArNet-ECG outperformed ArNet2 thus demonstrating that using the raw ECG provides added performance over the beat-to-beat interval time series. The main reason found for explaining the higher performance of ArNet-ECG was its high performance on atrial flutter examples versus poor performance on these recordings for ArNet2.

eess.SP↗

arXiv2022

Atrial Fibrillation Recurrence Risk Prediction from 12-lead ECG Recorded Pre- and Post-Ablation Procedure

Introduction: 12-lead electrocardiogram (ECG) is recorded during atrial fibrillation (AF) catheter ablation procedure (CAP). It is not easy to determine if CAP was successful without a long follow-up assessing for AF recurrence (AFR). Therefore, an AFR risk prediction algorithm could enable a better management of CAP patients. In this research, we extracted features from 12-lead ECG recorded before and after CAP and train an AFR risk prediction machine learning model. Methods: Pre- and post-CAP segments were extracted from 112 patients. The analysis included a signal quality criterion, heart rate variability and morphological biomarkers engineered from the 12-lead ECG (804 features overall). 43 out of the 112 patients (n) had AFR clinical endpoint available. These were utilized to assess the feasibility of AFR risk prediction, using either pre or post CAP features. A random forest classifier was trained within a nested cross validation framework. Results: 36 features were found statistically significant for distinguishing between the pre and post surgery states (n=112). For the classification, an area under the receiver operating characteristic (AUROC) curve was reported with AUROC_pre=0.64 and AUROC_post=0.74 (n=43). Discussion and conclusions: This preliminary analysis showed the feasibility of AFR risk prediction. Such a model could be used to improve CAP management.

cs.LG↗

arXiv2022

Building Trust: Lessons from the Technion-Rambam Machine Learning in Healthcare Datathon Event

A datathon is a time-constrained competition involving data science applied to a specific problem. In the past decade, datathons have been shown to be a valuable bridge between fields and expertise . Biomedical data analysis represents a challenging area requiring collaboration between engineers, biologists and physicians to gain a better understanding of patient physiology and of guide decision processes for diagnosis, prognosis and therapeutic interventions to improve care practice. Here, we reflect on the outcomes of an event that we organized in Israel at the end of March 2022 between the MIT Critical Data group, Rambam Health Care Campus (Rambam) and the Technion Israel Institute of Technology (Technion) in Haifa. Participants were asked to complete a survey about their skills and interests, which enabled us to identify current needs in machine learning training for medical problem applications. This work describes opportunities and limitations in medical data science in the Israeli context.

cs.DB↗

arXiv2022

PVBM: A Python Vasculature Biomarker Toolbox Based On Retinal Blood Vessel Segmentation

Introduction: Blood vessels can be non-invasively visualized from a digital fundus image (DFI). Several studies have shown an association between cardiovascular risk and vascular features obtained from DFI. Recent advances in computer vision and image segmentation enable automatising DFI blood vessel segmentation. There is a need for a resource that can automatically compute digital vasculature biomarkers (VBM) from these segmented DFI. Methods: In this paper, we introduce a Python Vasculature BioMarker toolbox, denoted PVBM. A total of 11 VBMs were implemented. In particular, we introduce new algorithmic methods to estimate tortuosity and branching angles. Using PVBM, and as a proof of usability, we analyze geometric vascular differences between glaucomatous patients and healthy controls. Results: We built a fully automated vasculature biomarker toolbox based on DFI segmentations and provided a proof of usability to characterize the vascular changes in glaucoma. For arterioles and venules, all biomarkers were significant and lower in glaucoma patients compared to healthy controls except for tortuosity, venular singularity length and venular branching angles. Conclusion: We have automated the computation of 11 VBMs from retinal blood vessel segmentation. The PVBM toolbox is made open source under a GNU GPL 3 license and is available on physiozoo.com (following publication).

cs.CV↗

arXiv2022

Generalizable and Robust Deep Learning Algorithm for Atrial Fibrillation Diagnosis Across Ethnicities, Ages and Sexes

To drive health innovation that meets the needs of all and democratize healthcare, there is a need to assess the generalization performance of deep learning (DL) algorithms across various distribution shifts to ensure that these algorithms are robust. This retrospective study is, to the best of our knowledge, the first to develop and assess the generalization performance of a deep learning (DL) model for AF events detection from long term beat-to-beat intervals across ethnicities, ages and sexes. The new recurrent DL model, denoted ArNet2, was developed on a large retrospective dataset of 2,147 patients totaling 51,386 hours of continuous electrocardiogram (ECG). The models generalization was evaluated on manually annotated test sets from four centers (USA, Israel, Japan and China) totaling 402 patients. The model was further validated on a retrospective dataset of 1,730 consecutives Holter recordings from the Rambam Hospital Holter clinic, Haifa, Israel. The model outperformed benchmark state-of-the-art models and generalized well across ethnicities, ages and sexes. Performance was higher for female than male and young adults (less than 60 years old) and showed some differences across ethnicities. The main finding explaining these variations was an impairment in performance in groups with a higher prevalence of atrial flutter (AFL). Our findings on the relative performance of ArNet2 across groups may have clinical implications on the choice of the preferred AF examination method to use relative to the group of interest.

cs.LG↗

arXiv2022

On Merging Feature Engineering and Deep Learning for Diagnosis, Risk-Prediction and Age Estimation Based on the 12-Lead ECG

Objective: Machine learning techniques have been used extensively for 12-lead electrocardiogram (ECG) analysis. For physiological time series, deep learning (DL) superiority to feature engineering (FE) approaches based on domain knowledge is still an open question. Moreover, it remains unclear whether combining DL with FE may improve performance. Methods: We considered three tasks intending to address these research gaps: cardiac arrhythmia diagnosis (multiclass-multilabel classification), atrial fibrillation risk prediction (binary classification), and age estimation (regression). We used an overall dataset of 2.3M 12-lead ECG recordings to train the following models for each task: i) a random forest taking the FE as input was trained as a classical machine learning approach; ii) an end-to-end DL model; and iii) a merged model of FE+DL. Results: FE yielded comparable results to DL while necessitating significantly less data for the two classification tasks and it was outperformed by DL for the regression task. For all tasks, merging FE with DL did not improve performance over DL alone. Conclusion: We found that for traditional 12-lead ECG based diagnosis tasks DL did not yield a meaningful improvement over FE, while it improved significantly the nontraditional regression task. We also found that combining FE with DL did not improve over DL alone which suggests that the FE were redundant with the features learned by DL. Significance: Our findings provides important recommendations on what machine learning strategy and data regime to chose with respect to the task at hand for the development of new machine learning models based on the 12-lead ECG.

cs.LG↗

arXiv2022

Machine Learning to Support Triage of Children at Risk for Epileptic Seizures in the Pediatric Intensive Care Unit

Objective: Epileptic seizures are relatively common in critically-ill children admitted to the pediatric intensive care unit (PICU) and thus serve as an important target for identification and treatment. Most of these seizures have no discernible clinical manifestation but still have a significant impact on morbidity and mortality. Children that are deemed at risk for seizures within the PICU are monitored using continuous-electroencephalogram (cEEG). cEEG monitoring cost is considerable and as the number of available machines is always limited, clinicians need to resort to triaging patients according to perceived risk in order to allocate resources. This research aims to develop a computer aided tool to improve seizures risk assessment in critically-ill children, using an ubiquitously recorded signal in the PICU, namely the electrocardiogram (ECG). Approach: A novel data-driven model was developed at a patient-level approach, based on features extracted from the first hour of ECG recording and the clinical data of the patient. Main results: The most predictive features were the age of the patient, the brain injury as coma etiology and the QRS area. For patients without any prior clinical data, using one hour of ECG recording, the classification performance of the random forest classifier reached an area under the receiver operating characteristic curve (AUROC) score of 0.84. When combining ECG features with the patients clinical history, the AUROC reached 0.87. Significance: Taking a real clinical scenario, we estimated that our clinical decision support triage tool can improve the positive predictive value by more than 59% over the clinical standard.

cs.LG↗

arXiv2022

SleepPPG-Net: a deep learning algorithm for robust sleep staging from continuous photoplethysmography

Introduction: Sleep staging is an essential component in the diagnosis of sleep disorders and management of sleep health. It is traditionally measured in a clinical setting and requires a labor-intensive labeling process. We hypothesize that it is possible to perform robust 4-class sleep staging using the raw photoplethysmography (PPG) time series and modern advances in deep learning (DL). Methods: We used two publicly available sleep databases that included raw PPG recordings, totalling 2,374 patients and 23,055 hours. We developed SleepPPG-Net, a DL model for 4-class sleep staging from the raw PPG time series. SleepPPG-Net was trained end-to-end and consists of a residual convolutional network for automatic feature extraction and a temporal convolutional network to capture long-range contextual information. We benchmarked the performance of SleepPPG-Net against models based on the best-reported state-of-the-art (SOTA) algorithms. Results: When benchmarked on a held-out test set, SleepPPG-Net obtained a median Cohen's Kappa ($κ$) score of 0.75 against 0.69 for the best SOTA approach. SleepPPG-Net showed good generalization performance to an external database, obtaining a $κ$ score of 0.74 after transfer learning. Perspective: Overall, SleepPPG-Net provides new SOTA performance. In addition, performance is high enough to open the path to the development of wearables that meet the requirements for usage in clinical applications such as the diagnosis and monitoring of obstructive sleep apnea.

cs.LG↗

arXiv2021

From sleep medicine to medicine during sleep: A clinical perspective

Sleep has a profound influence on the physiology of body systems and biological processes. Molecular studies have shown circadian-regulated shifts in protein expression patterns across human tissues, further emphasizing the unique functional, behavioral and pharmacokinetic landscape of sleep. Thus, many pathological processes are also expected to exhibit sleep-specific manifestations. Nevertheless, sleep is seldom utilized for the study, detection and treatment of non-sleep-specific pathologies. Modern advances in biosensor technologies have enabled remote, non-invasive recording of a growing number of physiologic parameters and biomarkers. Sleep is an ideal time frame for the collection of long and clean physiological time series data which can then be analyzed using data-driven algorithms such as deep learning. In this perspective paper, we aim to highlight the potential of sleep as an auspicious time for diagnosis, management and therapy of nonsleep-specific pathologies. We introduce key clinical studies in selected medical fields, which leveraged novel technologies and the advantageous period of sleep to diagnose, monitor and treat pathologies. We then discuss possible opportunities to further harness this new paradigm and modern technologies to explore human health and disease during sleep and to advance the development of novel clinical applications: From sleep medicine to medicine during sleep.

q-bio.QM↗

arXiv2020

Machine learning for nocturnal diagnosis of chronic obstructive pulmonary disease using digital oximetry biomarkers

Objective: Chronic obstructive pulmonary disease (COPD) is a highly prevalent chronic condition. COPD is a major source of morbidity, mortality and healthcare costs. Spirometry is the gold standard test for a definitive diagnosis and severity grading of COPD. However, a large proportion of individuals with COPD are undiagnosed and untreated. Given the high prevalence of COPD and its clinical importance, it is critical to develop new algorithms to identify undiagnosed COPD, especially in specific groups at risk, such as those with sleep disorder breathing. To our knowledge, no research has looked at the feasibility of COPD diagnosis from the nocturnal oximetry time series. Approach: We hypothesize that patients with COPD will exert certain patterns and/or dynamics of their overnight oximetry time series that are unique to this condition. We introduce a novel approach to nocturnal COPD diagnosis using 44 oximetry digital biomarkers and 5 demographic features and assess its performance in a population sample at risk of sleep-disordered breathing. A total of n=350 unique patients polysomnography (PSG) recordings. A random forest (RF) classifier is trained using these features and evaluated using the nested cross-validation procedure. Significance: Our research makes a number of novel scientific contributions. First, we demonstrated for the first time, the feasibility of COPD diagnosis from nocturnal oximetry time series in a population sample at risk of sleep disordered breathing. We highlighted what digital oximetry biomarkers best reflect how COPD manifests overnight. The results motivate that overnight single channel oximetry is a valuable pathway for COPD diagnosis.

eess.SP↗

arXiv2020

Remote health monitoring and diagnosis in the time of COVID-19

Coronavirus disease (COVID-19) is caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) that is rapidly spreading across the globe. The clinical spectrum of SARS-CoV-2 pneumonia ranges from mild to critically ill cases and requires early detection and monitoring, within a clinical environment for critical cases and remotely for mild cases. The fear of contamination in clinical environments has led to a dramatic reduction in on-site referrals for routine care. There has also been a perceived need to continuously monitor non-severe COVID- 19 patients, either from their quarantine site at home, or dedicated quarantine locations (e.g., hotels). Thus, the pandemic has driven incentives to innovate and enhance or create new routes for providing healthcare services at distance. In particular, this has created a dramatic impetus to find innovative ways to remotely and effectively monitor patient health status. In this paper we present a short review of remote health monitoring initiatives taken in 19 states during the time of the pandemic. We emphasize in the discussion particular aspects that are common ground for the reviewed states, in particular the future impact of the pandemic on remote health monitoring and consideration on data privacy.

cs.CY↗

arXiv2020

Digital biomarkers and artificial intelligence for mass diagnosis of atrial fibrillation in a population sample at risk of sleep disordered breathing

Atrial fibrillation (AF) is the most prevalent arrhythmia and is associated with a five-fold increase in stroke risk. Many individuals with AF go undetected. These individuals are often asymptomatic. There are ongoing debates on whether mass screening for AF is to be recommended. However, there is incentive in performing screening for specific at risk groups such as individuals suspected of sleep-disordered breathing where an important association between AF and obstructive sleep apnea (OSA) has been demonstrated. We introduce a new methodology leveraging digital biomarkers and recent advances in artificial intelligence (AI) for the purpose of mass AF diagnosis. We demonstrate the value of such methodology in a large population sample at risk of sleep disordered breathing. Four databases, totaling n=3,088 patients and p=26,913 hours of ECG raw data were used. Three of the databases (n=125, p=2,513) were used for training a machine learning model in recognizing AF events from beat-to-beat interval time series. The visit 1 of the sleep heart health study database (SHHS1, n=2,963, p=24,400) consists of overnight polysomnographic (PSG) recordings, and was considered as the test set. In SHHS1, expert inspection identified a total of 70 patients with a prominent AF rhythm. Model prediction on the SHHS1 showed an overall Se=0.97,Sp=0.99,NPV=0.99,PPV=0.67 in classifying individuals with or without prominent AF. PPV was non-inferior (p=0.03) for individuals with an apnea-hypopnea index (AHI) > 15 versus AHI < 15. Over 22% of correctly identified prominent AF rhythm cases were not documented as AF in the SHHS1. Individuals with prominent AF can be automatically diagnosed from an overnight single channel ECG recording, with an accuracy unaffected by the presence of OSA. AF detection from overnight ECG recording revealed a large proportion of undiagnosed AF and may enhance the phenotyping of OSA.

eess.SP↗