{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"Research Square"}],"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:16:18Z","timestamp":1783106178961,"version":"3.54.6"},"posted":{"date-parts":[[2026,3,26]]},"group-title":"In Review","reference-count":0,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,3,7]]},"abstract":"<title>Abstract<\/title>\n                <p>Large language models (LLMs) can automate clinical document summary generation. However, even clinically accurate outputs often fail to reflect individual clinicians\u2019 writing styles, leading to substantial post-editing. We examine this stylistic gap using a multi-author corpus of de-identified clinical summaries. We propose a style-informed generation framework that extracts clinician-specific stylistic features through LLM feedback and applies a Train\u2192Generate paradigm to produce personalized clinical summaries. Conventional metrics (ROUGE, BERTScore, cosine similarity) largely failed to distinguish intra-author from inter-author writing patterns, while Jaro-Winkler and BLEU demonstrated limited sensitivity. Targeted LLM-guided feature extraction\u2014emphasizing rhythm, narration, and sentence or list structure\u2014improved authorship classification up to 73% of accuracy. In blinded clinician A\/B testing, GPT-4-generated drafts were preferred less often than original notes, whereas the Gemini 2.5 Pro pipeline produced drafts preferred at rates comparable to, and in some cases exceeding, clinician-authored summaries. While inherent hallucination risks were noted, they were mitigated via high-fidelity prompt engineering and explicit adherence to source-only data constraints. These results suggest that style-informed generation can reduce the style gap and produce clinically acceptable clinical summaries that better align with the clinician\u2019s voice.<\/p>","DOI":"10.21203\/rs.3.rs-9054955\/v1","type":"posted-content","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T13:00:33Z","timestamp":1774530033000},"source":"Crossref","is-referenced-by-count":0,"title":["Decoding Clinician Authorial Style: A Style-Informed Pipeline for Clinical Document Summary Generation with Large Language Models"],"prefix":"10.21203","author":[{"given":"Scott","family":"Zhao","sequence":"first","affiliation":[{"name":"Wake Forest University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abbas","family":"Alili","sequence":"additional","affiliation":[{"name":"Wake Forest University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Usman","family":"Afzaal","sequence":"additional","affiliation":[{"name":"The Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammet F.","family":"Demir","sequence":"additional","affiliation":[{"name":"Wake Forest University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Lu","sequence":"additional","affiliation":[{"name":"Wake Forest University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Padageshwar","family":"Sunkara","sequence":"additional","affiliation":[{"name":"Wake Forest University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Metin N.","family":"Gurcan","sequence":"additional","affiliation":[{"name":"Wake Forest University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","container-title":[],"original-title":[],"link":[{"URL":"https:\/\/www.researchsquare.com\/article\/rs-9054955\/v1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.researchsquare.com\/article\/rs-9054955\/v1.html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T18:24:51Z","timestamp":1783103091000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.researchsquare.com\/article\/rs-9054955\/v1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":0,"URL":"https:\/\/doi.org\/10.21203\/rs.3.rs-9054955\/v1","relation":{},"subject":[],"published":{"date-parts":[[2026,3,26]]},"subtype":"preprint"}}