{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T01:04:03Z","timestamp":1755219843930,"version":"3.43.0"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"type":"electronic","value":"9781643686080"}],"license":[{"start":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T00:00:00Z","timestamp":1754524800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,7]]},"abstract":"<jats:p>In this study, we combined automatically generated labels from large language models (LLMs) with a small number of manual annotations to classify adverse event\u2013related treatment discontinuations in Japanese EHRs. By fine-tuning JMedRoBERTa and T5 on 6,156 LLM-labeled records and 200 manually labeled samples and then evaluating on a 100-record test set, T5 achieved a precision of 0.83, albeit with a recall of only 0.25. We noted that when training solely on the 200 human-labeled samples (that contained significantly few positive cases), the model failed to detect any adverse events, making a reliable measurement of precision or recall infeasible (that is, N\/A). This underscores the potential of large-scale LLM-driven labeling as well as the need to improve recall and label quality in practical clinical scenarios.<\/jats:p>","DOI":"10.3233\/shti251017","type":"book-chapter","created":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T11:38:16Z","timestamp":1754566696000},"source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models Can be Good Medical Annotators: A Case Study of Drug Change Detection in Japanese EHRs"],"prefix":"10.3233","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2513-8136","authenticated-orcid":false,"given":"Takeshi","family":"Ito","sequence":"first","affiliation":[{"name":"Nara Institute of Science and Technology, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohide","family":"Yoshie","sequence":"additional","affiliation":[{"name":"National Cerebral and Cardiovascular Center, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sohei","family":"Yoshimura","sequence":"additional","affiliation":[{"name":"National Cerebral and Cardiovascular Center, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuyuki","family":"Ohara","sequence":"additional","affiliation":[{"name":"Kobe City Medical Center General Hospital, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuntaro","family":"Yada","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shoko","family":"Wakamiya","sequence":"additional","affiliation":[{"name":"Nara Institute of Science and Technology, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eiji","family":"Aramaki","sequence":"additional","affiliation":[{"name":"University of Tsukuba, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Studies in Health Technology and Informatics","MEDINFO 2025 \u2014 Healthcare Smart \u00d7 Medicine Deep"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SHTI251017","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,7]],"date-time":"2025-08-07T11:38:16Z","timestamp":1754566696000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SHTI251017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,7]]},"ISBN":["9781643686080"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/shti251017","relation":{},"ISSN":["0926-9630","1879-8365"],"issn-type":[{"type":"print","value":"0926-9630"},{"type":"electronic","value":"1879-8365"}],"subject":[],"published":{"date-parts":[[2025,8,7]]}}}