Noam Keidar1, Yonatan Elul1,2, Assaf Schuster2, Yael Yaniv1. 1. Laboratory of Bioenergetic and Bioelectric Systems, Biomedical Engineering Faculty, Technion-Israel Institute of Technology (IIT), Haifa, Israel. 2. Computer Science Department, Technion-Israel Institute of Technology (IIT), Haifa, Israel.
Abstract
BACKGROUND: Screening the general public for atrial fibrillation (AF) may enable early detection and timely intervention, which could potentially decrease the incidence of stroke. Existing screening methods require professional monitoring and involve high costs. AF is characterized by an irregular irregularity of the cardiac rhythm, which may be detectable using an index quantifying and visualizing this type of irregularity, motivating wide screening programs and promoting the research of AF patient subgroups and clinical impact of AF burden. METHODS: We calculated variability, normality and mean of the difference between consecutive RR interval series (denoted as modified entropy scale-MESC) to quantify irregular irregularities. Based on the variability and normality indices calculated for long 1-lead ECG records, we created a plot termed a regularogram (RGG), which provides a visual presentation of irregularly irregular rates and their burden in a given record. To inspect the potency of these indices, they were applied to train and test a machine learning classifier to identify AF episodes in gold-standard, publicly available databases (PhysioNet) that include recordings from both patients with AF and/or other rhythm disturbances, and from healthy volunteers. The classifier was trained and validated on one database and tested on three other databases. RESULTS: Irregular irregularities were identified using normality, variability and mean MESC indices. The RGG displayed visually distinct differences between patients with vs. without AF and between patients with different levels of AF burden. Training a simple, explainable machine learning tool integrating these three indices enabled AF detection with 99.9% accuracy, when trained on the same person, and 97.8%, when trained on patients from a different database. Comparison to other RR interval-based AF detection methods that utilize signal processing, classic machine learning and deep learning techniques, showed superiority of our suggested method. CONCLUSION: Visualizing and quantifying irregular irregularities will be of value for both rapid visual inspection of long Holter recordings for the presence and the burden of AF, and for machine learning classification to identify AF episodes. A free online tool for calculating the indices, drawing RGGs and estimating AF burden, is available.
BACKGROUND: Screening the general public for atrial fibrillation (AF) may enable early detection and timely intervention, which could potentially decrease the incidence of stroke. Existing screening methods require professional monitoring and involve high costs. AF is characterized by an irregular irregularity of the cardiac rhythm, which may be detectable using an index quantifying and visualizing this type of irregularity, motivating wide screening programs and promoting the research of AF patient subgroups and clinical impact of AF burden. METHODS: We calculated variability, normality and mean of the difference between consecutive RR interval series (denoted as modified entropy scale-MESC) to quantify irregular irregularities. Based on the variability and normality indices calculated for long 1-lead ECG records, we created a plot termed a regularogram (RGG), which provides a visual presentation of irregularly irregular rates and their burden in a given record. To inspect the potency of these indices, they were applied to train and test a machine learning classifier to identify AF episodes in gold-standard, publicly available databases (PhysioNet) that include recordings from both patients with AF and/or other rhythm disturbances, and from healthy volunteers. The classifier was trained and validated on one database and tested on three other databases. RESULTS: Irregular irregularities were identified using normality, variability and mean MESC indices. The RGG displayed visually distinct differences between patients with vs. without AF and between patients with different levels of AF burden. Training a simple, explainable machine learning tool integrating these three indices enabled AF detection with 99.9% accuracy, when trained on the same person, and 97.8%, when trained on patients from a different database. Comparison to other RR interval-based AF detection methods that utilize signal processing, classic machine learning and deep learning techniques, showed superiority of our suggested method. CONCLUSION: Visualizing and quantifying irregular irregularities will be of value for both rapid visual inspection of long Holter recordings for the presence and the burden of AF, and for machine learning classification to identify AF episodes. A free online tool for calculating the indices, drawing RGGs and estimating AF burden, is available.
Authors: Gregory Y H Lip; Laurent Fauchier; Saul B Freedman; Isabelle Van Gelder; Andrea Natale; Carola Gianni; Stanley Nattel; Tatjana Potpara; Michiel Rienstra; Hung-Fat Tse; Deirdre A Lane Journal: Nat Rev Dis Primers Date: 2016-03-31 Impact factor: 52.329
Authors: Sumeet S Chugh; Rasmus Havmoeller; Kumar Narayanan; David Singh; Michiel Rienstra; Emelia J Benjamin; Richard F Gillum; Young-Hoon Kim; John H McAnulty; Zhi-Jie Zheng; Mohammad H Forouzanfar; Mohsen Naghavi; George A Mensah; Majid Ezzati; Christopher J L Murray Journal: Circulation Date: 2013-12-17 Impact factor: 29.690
Authors: Yonatan Elul; Aviv A Rosenberg; Assaf Schuster; Alex M Bronstein; Yael Yaniv Journal: Proc Natl Acad Sci U S A Date: 2021-06-15 Impact factor: 11.205