{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T15:56:04Z","timestamp":1775922964909,"version":"3.50.1"},"posted":{"date-parts":[[2022,8,16]]},"group-title":"Health Informatics","reference-count":58,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,4,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Cardiac auscultation is an accessible diagnostic screening tool that can help to identify patients with heart murmurs for follow-up diagnostic screening and treatment for abnormal cardiac function. However, experts are needed to interpret the heart sounds, limiting the accessibility of auscultation for cardiac care 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 the heart sounds.<\/jats:p>\n                <jats:p>For the Challenge, we sourced 5272 PCG recordings from 1568 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 code for training and running their algorithms, improving the transparency, reproducibility, and utility of their work. We also devised an evaluation metric that considered the costs of screening, diagnosis, treatment, and diagnostic errors, allowing us to investigate the benefits of algorithmic diagnostic screening and facilitate the development of more clinically relevant algorithms.<\/jats:p>\n                <jats:p>We received 779 algorithms from 87 teams during the course of the Challenge, resulting in 53 working codebases for detecting heart murmurs and abnormal cardiac function from PCGs. These algorithms represent a diversity of approaches from both academia and industry.<\/jats:p>\n                <jats:p>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 accessible pre-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.<\/jats:p>\n                <jats:sec>\n                  <jats:title>Author summary<\/jats:title>\n                  <jats:p>Cardiac auscultation is an accessible diagnostic screening tool for identifying heart murmurs. However, experts are needed to interpret heart sounds, limiting the accessibility of auscultation in cardiac care. The George B. Moody PhysioNet Challenge 2022 invited teams to develop algorithms for detecting heart murmurs and abnormal cardiac function from phonocardiogram (PCG) recordings of heart sounds.<\/jats:p>\n                  <jats:p>For the Challenge, we sourced 5272 PCG recordings from 1568 pediatric patients in rural Brazil. We required the participants to submit the complete code for training and running their algorithms, improving the transparency, reproducibility, and utility of their work. We also devised an evaluation metric that considered the costs of screening, diagnosis, treatment, and diagnostic errors, 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 and publications that represented a diversity of approaches to detecting heart murmurs and identifying clinical outcomes from heart sound recordings.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2022.08.11.22278688","type":"posted-content","created":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T11:35:11Z","timestamp":1660649711000},"source":"Crossref","is-referenced-by-count":19,"title":["Heart murmur detection from phonocardiogram recordings: The George B. Moody PhysioNet Challenge 2022"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4688-7965","authenticated-orcid":false,"given":"Matthew A.","family":"Reyna","sequence":"first","affiliation":[]},{"given":"Yashar","family":"Kiarashi","sequence":"additional","affiliation":[]},{"given":"Andoni","family":"Elola","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Oliveira","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"Renna","sequence":"additional","affiliation":[]},{"given":"Annie","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Erick A.","family":"Perez Alday","sequence":"additional","affiliation":[]},{"given":"Nadi","family":"Sadr","sequence":"additional","affiliation":[]},{"given":"Ashish","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Jacques","family":"Kpodonu","sequence":"additional","affiliation":[]},{"given":"Sandra","family":"Mattos","sequence":"additional","affiliation":[]},{"given":"Miguel T.","family":"Coimbra","sequence":"additional","affiliation":[]},{"given":"Reza","family":"Sameni","sequence":"additional","affiliation":[]},{"given":"Ali Bahrami","family":"Rad","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5709-201X","authenticated-orcid":false,"given":"Gari D.","family":"Clifford","sequence":"additional","affiliation":[]}],"member":"54368","reference":[{"issue":"1","key":"2023040805300420000_2022.08.11.22278688v2.1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2174\/2213275910801010001","article-title":"Features for heartbeat sound signal normal and pathological","volume":"1","year":"2008","journal-title":"Recent Patents on Computer Science"},{"key":"2023040805300420000_2022.08.11.22278688v2.2","doi-asserted-by":"publisher","DOI":"10.1080\/03091900500282772"},{"key":"2023040805300420000_2022.08.11.22278688v2.3","doi-asserted-by":"publisher","DOI":"10.1001\/archinte.166.6.617"},{"key":"2023040805300420000_2022.08.11.22278688v2.4","doi-asserted-by":"publisher","DOI":"10.1378\/chest.91.6.870"},{"key":"2023040805300420000_2022.08.11.22278688v2.5","first-page":"278","article-title":"In: Webster JG, editor","volume":"5. 2nd","year":"2006","journal-title":"Encyclopedia of Medical Devices and Instrumentation"},{"key":"2023040805300420000_2022.08.11.22278688v2.6","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2021.3137048"},{"key":"2023040805300420000_2022.08.11.22278688v2.7","doi-asserted-by":"publisher","DOI":"10.1088\/0967-3334\/37\/12\/2181"},{"key":"2023040805300420000_2022.08.11.22278688v2.8","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2018.2841197"},{"key":"2023040805300420000_2022.08.11.22278688v2.9","doi-asserted-by":"publisher","DOI":"10.1109\/jbhi.2019.2894222"},{"key":"2023040805300420000_2022.08.11.22278688v2.10","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-6-11-1371"},{"key":"2023040805300420000_2022.08.11.22278688v2.11","doi-asserted-by":"publisher","DOI":"10.1161\/01.CIR.101.23.e215"},{"key":"2023040805300420000_2022.08.11.22278688v2.12","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000004145"},{"key":"2023040805300420000_2022.08.11.22278688v2.13","doi-asserted-by":"publisher","DOI":"10.1257\/pandp.20211078"},{"key":"2023040805300420000_2022.08.11.22278688v2.14","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2022.10561"},{"key":"2023040805300420000_2022.08.11.22278688v2.15","doi-asserted-by":"crossref","unstructured":"Friedman JH . Greedy function approximation: a gradient boosting machine. Annals of statistics. 2001; p. 1189\u20131232.","DOI":"10.1214\/aos\/1013203451"},{"key":"2023040805300420000_2022.08.11.22278688v2.16","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining; 2016. p. 785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"2023040805300420000_2022.08.11.22278688v2.17","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2023040805300420000_2022.08.11.22278688v2.18","first-page":"1","volume":"49","year":"2022","journal-title":"A Lightweight Robust Approach for Automatic Heart Murmurs and Clinical Outcomes Classification from Phonocardiogram Recordings"},{"key":"2023040805300420000_2022.08.11.22278688v2.19","first-page":"1","volume":"49","year":"2022","journal-title":"Detection of Heart Murmurs in Phonocardiograms with Parallel Hidden Semi-Markov Models"},{"key":"2023040805300420000_2022.08.11.22278688v2.20","first-page":"1","volume":"49","year":"2022","journal-title":"Hierarchical Multi-Scale Convolutional Network for Murmurs Detection on PCG Signals"},{"key":"2023040805300420000_2022.08.11.22278688v2.21","first-page":"1","volume":"49","year":"2022","journal-title":"Dual Bayesian ResNet: A Deep Learning Approach to Heart Murmur Detection"},{"key":"2023040805300420000_2022.08.11.22278688v2.22","first-page":"1","volume":"49","year":"2022","journal-title":"Deep Learning Based Heart Murmur Detection using Frequency-time Domain Features of Heartbeat Sounds"},{"key":"2023040805300420000_2022.08.11.22278688v2.23","first-page":"1","volume":"49","year":"2022","journal-title":"Ensemble Transformer-Based Neural Networks Detect Heart Murmur In Phonocardiogram Recordings"},{"key":"2023040805300420000_2022.08.11.22278688v2.24","first-page":"1","volume":"49","year":"2022","journal-title":"Detection of Heart Sound Murmurs and Clinical Outcome with Bidirectional Long Short-Term Memory Networks"},{"key":"2023040805300420000_2022.08.11.22278688v2.25","first-page":"1","volume":"49","year":"2022","journal-title":"Murmur Identification Using Supervised Constrastive Learning"},{"key":"2023040805300420000_2022.08.11.22278688v2.26","first-page":"1","volume":"49","year":"2022","journal-title":"Classification of heart murmurs using an ensemble of residual CNNs"},{"key":"2023040805300420000_2022.08.11.22278688v2.27","first-page":"1","volume":"49","year":"2022","journal-title":"Two-stage Detection of Murmurs from Phonocardiograms using Deep and One-class Methods"},{"key":"2023040805300420000_2022.08.11.22278688v2.28","first-page":"1","volume":"49","year":"2022","journal-title":"Murmur Detection and Clinical Outcome Classification Using a VGG-like Network and Combined Time-Frequency Representations of PCG Signals"},{"key":"2023040805300420000_2022.08.11.22278688v2.29","first-page":"1","volume":"49","year":"2022","journal-title":"Two-Stage Multitask-Learner for PCG Murmur Location Detection"},{"key":"2023040805300420000_2022.08.11.22278688v2.30","first-page":"1","volume":"49","year":"2022","journal-title":"Listen to your heart: A self-supervised approach for detecting murmur in heart-beat sounds"},{"key":"2023040805300420000_2022.08.11.22278688v2.31","first-page":"1","volume":"49","year":"2022","journal-title":"Searching for Effective Neural Network Architectures for Heart Murmur Detection from Phonocardiogram"},{"key":"2023040805300420000_2022.08.11.22278688v2.32","first-page":"1","volume":"49","year":"2022","journal-title":"Multitask and Transfer Learning for Murmur Detection in Heart Sounds"},{"key":"2023040805300420000_2022.08.11.22278688v2.33","first-page":"1","volume":"49","year":"2022","journal-title":"Using Mel-Spectrograms and 2D-CNNs to detect Murmurs in Variable Length Phonocardiograms"},{"key":"2023040805300420000_2022.08.11.22278688v2.34","first-page":"1","volume":"49","year":"2022","journal-title":"Maiby\u2019s Algorithm: A Two-stage Deep Learning approach for Murmur Detection in Mel Spectrograms for Automatic Auscultation of Congenital Heart Disease"},{"key":"2023040805300420000_2022.08.11.22278688v2.35","first-page":"1","volume":"49","year":"2022","journal-title":"Heart Murmur Detection from Phonocardiogram Based on Residual Neural Network with Classes Distinguished Focal Loss"},{"key":"2023040805300420000_2022.08.11.22278688v2.36","first-page":"1","volume":"49","year":"2022","journal-title":"Modified Variable Kernel Length ResNets for Heart Murmur Detection and Clinical Outcome Prediction using Multi-positional Phonocardiogram Recording"},{"key":"2023040805300420000_2022.08.11.22278688v2.37","first-page":"1","volume":"49","year":"2022","journal-title":"Multi-Task Prediction of Murmur and Outcome from Heart Sound Recordings"},{"key":"2023040805300420000_2022.08.11.22278688v2.38","first-page":"1","volume":"49","year":"2022","journal-title":"Classification of Phonocardiogram Recordings using Vision Transformer Architecture"},{"key":"2023040805300420000_2022.08.11.22278688v2.39","first-page":"1","volume":"49","year":"2022","journal-title":"Learning Time-Frequency Representations of Phonocardiogram for Murmur Detection"},{"key":"2023040805300420000_2022.08.11.22278688v2.40","first-page":"1","volume":"49","year":"2022","journal-title":"Classification of phonocardiograms using residual convolutional neural network and MLP"},{"key":"2023040805300420000_2022.08.11.22278688v2.41","first-page":"1","volume":"49","year":"2022","journal-title":"Convolutional neural network aproach for heart MurMur detection in auscultation signals using wavelet transform based features"},{"key":"2023040805300420000_2022.08.11.22278688v2.42","first-page":"1","volume":"49","year":"2022","journal-title":"An LSTM-based Listener for Early Detection of Heart Disease"},{"key":"2023040805300420000_2022.08.11.22278688v2.43","first-page":"1","volume":"49","year":"2022","journal-title":"Detection of murmurs from heart sound recordings with deep residual networks"},{"key":"2023040805300420000_2022.08.11.22278688v2.44","first-page":"1","volume":"49","year":"2022","journal-title":"Phonocardiographic Murmur Detection by Scattering-Recurrent Networks"},{"key":"2023040805300420000_2022.08.11.22278688v2.45","first-page":"1","volume":"49","year":"2022","journal-title":"A Fusion of Handcrafted Features and Deep Learning Classifiers for Heart Murmur Detection"},{"key":"2023040805300420000_2022.08.11.22278688v2.46","first-page":"1","volume":"49","year":"2022","journal-title":"Beat-wise uncertainty learning for murmur detection in heart sounds"},{"key":"2023040805300420000_2022.08.11.22278688v2.47","first-page":"1","volume":"49","year":"2022","journal-title":"Phonocardiogram Classification Using 1-Dimensional Inception Time Convolutional Neural Networks"},{"key":"2023040805300420000_2022.08.11.22278688v2.48","first-page":"1","volume":"49","year":"2022","journal-title":"Murmur Classification with U-net State Prediction"},{"key":"2023040805300420000_2022.08.11.22278688v2.49","first-page":"1","volume":"49","year":"2022","journal-title":"Transfer Learning in Heart Sound Classification using Mel spectrogram"},{"key":"2023040805300420000_2022.08.11.22278688v2.50","first-page":"1","volume":"49","year":"2022","journal-title":"Heart Murmur Detection Using Wavelet Time Scattering and Support Vector Machines"},{"key":"2023040805300420000_2022.08.11.22278688v2.51","first-page":"1","volume":"49","year":"2022","journal-title":"Heart Murmur Detection of PCG Using ResNet with Selective Kernel Convolution"},{"key":"2023040805300420000_2022.08.11.22278688v2.52","first-page":"1","volume":"49","year":"2022","journal-title":"Classification of Murmurs in PCG Using Combined Frequency Domain and Physician Inspired Features"},{"key":"2023040805300420000_2022.08.11.22278688v2.53","first-page":"1","volume":"49","year":"2022","journal-title":"Heart Murmur Detection and Clinical Outcome Prediction using Multilayer Perceptron Classifier"},{"key":"2023040805300420000_2022.08.11.22278688v2.54","first-page":"1","volume":"49","year":"2022","journal-title":"Outcome Prediction and Murmur Detection in Sets of Phonocardiograms by a Deep Learning-Based Ensemble Approach"},{"key":"2023040805300420000_2022.08.11.22278688v2.55","first-page":"1","volume":"49","year":"2022","journal-title":"ACQuA: Anomaly Classification with Quasi-Attractors"},{"key":"2023040805300420000_2022.08.11.22278688v2.56","first-page":"1","volume":"49","year":"2022","journal-title":"Transformer embedded with learnable filters for heart murmur detection"},{"key":"2023040805300420000_2022.08.11.22278688v2.57","first-page":"1","volume":"49","year":"2022","journal-title":"Towards Uncertainty-Aware Murmur Detection in Heart Sounds via Tandem Learning"},{"key":"2023040805300420000_2022.08.11.22278688v2.58","first-page":"1","article-title":"AF Classification from a Short Single Lead ECG Recording: the PhysioNet\/Computing in Cardiology Challenge","volume":"44. IEEE; 2017","year":"2017","journal-title":"In: 2017 Computing in Cardiology (CinC)"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2022.08.11.22278688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T14:48:29Z","timestamp":1768488509000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2022.08.11.22278688"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,16]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1101\/2022.08.11.22278688","relation":{},"subject":[],"published":{"date-parts":[[2022,8,16]]},"subtype":"preprint"}}