{"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/190407640","title":"Medical device surveillance with electronic health records","arxiv_id":"1904.07640","date":"2019-04-03","proceeding":null,"authors":["Alison Callahan","Jason A. Fries","Christopher Ré","James I Huddleston III","Nicholas J Giori","Scott Delp","Nigam H. Shah"],"abstract":"Post-market medical device surveillance is a challenge facing manufacturers,\nregulatory agencies, and health care providers. Electronic health records are\nvaluable sources of real world evidence to assess device safety and track\ndevice-related patient outcomes over time. However, distilling this evidence\nremains challenging, as information is fractured across clinical notes and\nstructured records. Modern machine learning methods for machine reading promise\nto unlock increasingly complex information from text, but face barriers due to\ntheir reliance on large and expensive hand-labeled training sets. To address\nthese challenges, we developed and validated state-of-the-art deep learning\nmethods that identify patient outcomes from clinical notes without requiring\nhand-labeled training data. Using hip replacements as a test case, our methods\naccurately extracted implant details and reports of complications and pain from\nelectronic health records with up to 96.3% precision, 98.5% recall, and 97.4%\nF1, improved classification performance by 12.7- 53.0% over rule-based methods,\nand detected over 6 times as many complication events compared to using\nstructured data alone. Using these events to assess complication-free\nsurvivorship of different implant systems, we found significant variation\nbetween implants, including for risk of revision surgery, which could not be\ndetected using coded data alone. Patients with revision surgeries had more hip\npain mentions in the post-hip replacement, pre-revision period compared to\npatients with no evidence of revision surgery (mean hip pain mentions 4.97 vs.\n3.23; t = 5.14; p < 0.001). Some implant models were associated with higher or\nlower rates of hip pain mentions. Our methods complement existing surveillance\nmechanisms by requiring orders of magnitude less hand-labeled training data,\noffering a scalable solution for national medical device surveillance.","url_abs":"http://arxiv.org/abs/1904.07640v1","url_pdf":"http://arxiv.org/pdf/1904.07640v1.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":"190407640","repo_url":"https://github.com/som-shahlab/ehr-rwe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}