{"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/detection-of-paroxysmal-atrial-fibrillation","title":"Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks","arxiv_id":"1805.09133","date":"2018-05-07","proceeding":null,"authors":["Supreeth P. Shashikumar","Amit J. Shah","Gari. D. Clifford","Shamim Nemati"],"abstract":"Detection of atrial fibrillation (AF), a type of cardiac arrhythmia, is\ndifficult since many cases of AF are usually clinically silent and undiagnosed.\nIn particular paroxysmal AF is a form of AF that occurs occasionally, and has a\nhigher probability of being undetected. In this work, we present an attention\nbased deep learning framework for detection of paroxysmal AF episodes from a\nsequence of windows. Time-frequency representation of 30 seconds recording\nwindows, over a 10 minute data segment, are fed sequentially into a deep\nconvolutional neural network for image-based feature extraction, which are then\npresented to a bidirectional recurrent neural network with an attention layer\nfor AF detection. To demonstrate the effectiveness of the proposed framework\nfor transient AF detection, we use a database of 24 hour Holter\nElectrocardiogram (ECG) recordings acquired from 2850 patients at the\nUniversity of Virginia heart station. The algorithm achieves an AUC of 0.94 on\nthe testing set, which exceeds the performance of baseline models. We also\ndemonstrate the cross-domain generalizablity of the approach by adapting the\nlearned model parameters from one recording modality (ECG) to another\n(photoplethysmogram) with improved AF detection performance. The proposed high\naccuracy, low false alarm algorithm for detecting paroxysmal AF has potential\napplications in long-term monitoring using wearable sensors.","url_abs":"http://arxiv.org/abs/1805.09133v1","url_pdf":"http://arxiv.org/pdf/1805.09133v1.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":"detection-of-paroxysmal-atrial-fibrillation","repo_url":"https://github.com/chengding0713/awesome-ppg-af-detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atrial-fibrillation-detection","task_name":"Atrial Fibrillation Detection"},{"task_slug":"electrocardiography-ecg","task_name":"Electrocardiography (ECG)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}