{"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/ecgnet-learning-where-to-attend-for-detection-1","title":"ECGNET: Learning where to attend for detection of atrial fibrillation with deep visual attention","arxiv_id":"1812.07422","date":"2019-02-15","proceeding":"arXiv:1812.07422 2018 12","authors":[],"abstract":"The complexity of the patterns associated with Atrial Fibrillation (AF) and\nthe high level of noise affecting these patterns have significantly limited the\ncurrent signal processing and shallow machine learning approaches to get\naccurate AF detection results. Deep neural networks have shown to be very\npowerful to learn the non-linear patterns in the data. While a deep learning\napproach attempts to learn complex pattern related to the presence of AF in the\nECG, they can benefit from knowing which parts of the signal is more important\nto focus during learning. In this paper, we introduce a two-channel deep neural\nnetwork to more accurately detect AF presented in the ECG signal. The first\nchannel takes in a preprocessed ECG signal and automatically learns where to\nattend for detection of AF. The second channel simultaneously takes in the\npreprocessed ECG signal to consider all features of entire signals. The model\nshows via visualization that what parts of the given ECG signal are important\nto attend while trying to detect atrial fibrillation. In addition, this\ncombination significantly improves the performance of the atrial fibrillation\ndetection (achieved a sensitivity of 99.53%, specificity of 99.26% and accuracy\nof 99.40% on the MIT-BIH atrial fibrillation database with 5-s ECG segments.)","url_abs":"http://arxiv.org/abs/1812.07422v2","url_pdf":"http://arxiv.org/pdf/1812.07422v2.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":[],"tasks":[{"task_slug":"atrial-fibrillation-detection","task_name":"Atrial Fibrillation Detection"},{"task_slug":"specificity","task_name":"Specificity"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/atrial-fibrillation-detection-on-mit-bih-af","task":"Atrial Fibrillation Detection","dataset":"MIT-BIH AF","model":"ECGNET","rank_in_archive_order":1,"of":6,"metrics":{"Accuracy":"99.40%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}