{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/classification-of-12-lead-ecgs-the-physionet","title":"Classification of 12-lead ECGs: the PhysioNet/ Computing in Cardiology Challenge 2020","arxiv_id":null,"date":"2020-12-29","proceeding":"Computing in Cardiology 2020 12","authors":["Erick A. Perez Alday","Annie Gu","Amit Shah","Chad Robichaux","An-Kwok Ian Wong","Chengyu Liu","Feifei Liu","Ali Bahrami Rad","Andoni Elola","Salman Seyedi","Qiao Li","ASHISH SHARMA","Gari D. Clifford","Matthew A. Reyna"],"abstract":"Objective: Vast 12-lead ECGs repositories provide opportunities to develop new machine\r\nlearning approaches for creating accurate and automatic diagnostic systems for cardiac\r\nabnormalities. However, most 12-lead ECG classification studies are trained, tested, or\r\ndeveloped in single, small, or relatively homogeneous datasets. In addition, most algorithms\r\nfocus on identifying small numbers of cardiac arrhythmias that do not represent the\r\ncomplexity and difficulty of ECG interpretation. This work addresses these issues by\r\nproviding a standard, multi-institutional database and a novel scoring metric through a\r\npublic competition: the PhysioNet/Computing in Cardiology Challenge 2020.\r\nApproach: A total of 66361 12-lead ECG recordings were sourced from six hospital\r\nsystems from four countries across three continents. 43,101 recordings were posted publicly\r\nwith a focus on 27 diagnoses. For the first time in a public competition, we required teams\r\nto publish open-source code for both training and testing their algorithms, ensuring full\r\nscientific reproducibility.\r\nMain results: A total of 217 teams submitted 1395 algorithms during the Challenge,\r\nrepresenting a diversity of approaches for identifying cardiac abnormalities from both\r\nacademia and industry. As with previous Challenges, high-performing algorithms exhibited\r\nsignificant drops (/ 10%) in performance on the hidden test data.\r\nSignificance: Data from diverse institutions allowed us to assess algorithmic\r\ngeneralizability. A novel evaluation metric considered different misclassification errors for\r\ndifferent cardiac abnormalities, capturing the outcomes and risks of different diagnoses.\r\nRequiring both trained models and code for training models improved the generalizability\r\nof submissions, setting a new bar in reproducibility for public data science competitions.","url_abs":"https://iopscience.iop.org/article/10.1088/1361-6579/abc960","url_pdf":"https://moody-challenge.physionet.org/2020/papers/2020ChallengePaper.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"classification-of-12-lead-ecgs-the-physionet","repo_url":"https://github.com/physionetchallenges/python-classifier-2021","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"diagnostic","task_name":"Diagnostic"},{"task_slug":"ecg-classification","task_name":"ECG Classification"}],"methods":[],"datasets_introduced":[{"slug":"physionet-challenge-2020","name":"PhysioNet Challenge 2020","full_name":"PhysioNet Challenge 2020"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}