{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T09:48:25Z","timestamp":1775555305693,"version":"3.50.1"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643683881","type":"print"},{"value":"9781643683898","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T00:00:00Z","timestamp":1684368000000},"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":[[2023,5,18]]},"abstract":"<jats:p>Clinical information systems have become large repositories for semi-structured and partly annotated electronic health record data, which have reached a critical mass that makes them interesting for supervised data-driven neural network approaches. We explored automated coding of 50 character long clinical problem list entries using the International Classification of Diseases (ICD-10) and evaluated three different types of network architectures on the top 100 ICD-10 three-digit codes. A fastText baseline reached a macro-averaged F1-score of 0.83, followed by a character-level LSTM with a macro-averaged F1-score of 0.84. The top performing approach used a downstreamed RoBERTa model with a custom language model, yielding a macro-averaged F1-score of 0.88. A neural network activation analysis together with an investigation of the false positives and false negatives unveiled inconsistent manual coding as a main limiting factor.<\/jats:p>","DOI":"10.3233\/shti230267","type":"book-chapter","created":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T08:47:15Z","timestamp":1684486035000},"source":"Crossref","is-referenced-by-count":2,"title":["Secondary Use of Clinical Problem List Entries for Neural Network-Based Disease Code Assignment"],"prefix":"10.3233","author":[{"given":"Markus","family":"Kreuzthaler","sequence":"first","affiliation":[{"name":"Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bastian","family":"Pfeifer","sequence":"additional","affiliation":[{"name":"Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diether","family":"Kramer","sequence":"additional","affiliation":[{"name":"Department of Information and Process Management, Steierm\u00e4rkische Krankenanstaltengesellschaft m.b.H. (KAGes), Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stefan","family":"Schulz","sequence":"additional","affiliation":[{"name":"Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz, Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Studies in Health Technology and Informatics","Caring is Sharing \u2013 Exploiting the Value in Data for Health and Innovation"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/SHTI230267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,31]],"date-time":"2023-05-31T15:01:35Z","timestamp":1685545295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/SHTI230267"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,18]]},"ISBN":["9781643683881","9781643683898"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/shti230267","relation":{},"ISSN":["0926-9630","1879-8365"],"issn-type":[{"value":"0926-9630","type":"print"},{"value":"1879-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,18]]}}}