{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:42:54Z","timestamp":1785544974785,"version":"3.56.0"},"reference-count":42,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Lifestyle interventions for patients with prostate cancer have been shown to improve treatment adherence and quality of life. However, there remains a lack of large language models (LLMs) capable of delivering individualized and professional lifestyle recommendations under clearly defined medical safety boundaries and controlled evidence sources.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and evaluate a supervised fine-tuned LLM\u2014PCaPLMM_SFT (Prostate Cancer Patient Lifestyle Management Model via Supervised Fine-Tuning)\u2014to support health literacy improvement and lifestyle self-management among patients with prostate cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We searched English-language literature primarily from PubMed (February 2015 to February 2025) to build a structured lifestyle management knowledge base covering diet, physical activity, weight management, medication adherence, and psychological support. We used a retrieval-augmented generation pipeline to generate patient-style question-answer (QA) pairs from retrieved knowledge slices. Bilingual English-Chinese QA data were generated from English-language source evidence through patient-oriented reformulation and retrieval-augmented generation\u2013based answer generation, and independent English and Chinese test sets were constructed to assess bilingual QA performance. We trained Baichuan2-7B-Chat using a 2-stage strategy, consisting of continued pretraining, followed by supervised fine-tuning with low-rank adaptation. Model outputs were evaluated in 2 double-blind rounds by referee LLMs (Qwen3-Max and DeepSeek-R1) and compared with GPT-3.5-Turbo and the base Baichuan2-7B-Chat using 2500 queries across 5 lifestyle scenarios. Additionally, 3 domain experts conducted a blinded review of 50 QA samples (10 per scenario). We used the Mann-Whitney\n                      <jats:italic>U<\/jats:italic>\n                      test with effect size\n                      <jats:italic>r<\/jats:italic>\n                      , and Benjamini-Hochberg false discovery rate correction, and examined consistency using intraclass correlation coefficients.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Based on 2211 included publications, we constructed the PCaPLMM_SFT-Train dataset. The knowledge base yielded &gt;150,000 structured knowledge slices. After 2 rounds of review, we obtained 42,330 single-turn QA pairs and 3008 multiturn dialogues, and the supervised fine-tuning phase used 45,338 structured QA samples. In the dual-round referee LLM assessment, PCaPLMM_SFT consistently outperformed Baichuan2-7B-Chat across dimensions and showed comparable or superior performance to GPT-3.5-Turbo across 5 lifestyle scenarios. Consistency analyses indicated moderate to good agreement between referee models across rounds, supporting the robustness of the comparative evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>PCaPLMM_SFT demonstrates the feasibility of constructing a medical lifestyle\u2013focused LLM by integrating structured medical knowledge, QA-style training data, and a multilayer evaluation system. This framework provides a reproducible methodological foundation for evidence-based health education and lifestyle management and establishes groundwork for future evaluation in real-world health management settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/92663","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T19:12:06Z","timestamp":1784661126000},"page":"e92663-e92663","source":"Crossref","is-referenced-by-count":0,"title":["A Supervised Fine-Tuned Large Language Model for Lifestyle Management in Patients With Prostate Cancer: Development and Evaluation Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6777-6753","authenticated-orcid":false,"given":"Fangyuan","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1577-3020","authenticated-orcid":false,"given":"Qiuwen","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0469-805X","authenticated-orcid":false,"given":"Xin","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8910-5186","authenticated-orcid":false,"given":"Nan","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0920-2502","authenticated-orcid":false,"given":"Jiayi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6771-5446","authenticated-orcid":false,"given":"Tu","family":"Lan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6603-6112","authenticated-orcid":false,"given":"Yuanjun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6543-0317","authenticated-orcid":false,"given":"Yuxin","family":"Lin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0327-7385","authenticated-orcid":false,"given":"Kui","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8228-0787","authenticated-orcid":false,"given":"Yalan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"R1","doi-asserted-by":"publisher","DOI":"10.1093\/database\/baz154","article-title":"PCaLiStDB: a lifestyle database for precision prevention of prostate cancer","volume":"2020","author":"Chen","journal-title":"Database (Oxford)"},{"key":"R2","doi-asserted-by":"publisher","DOI":"10.2196\/47102","article-title":"Effectiveness of a nurse-led mobile-based health coaching program for patients with prostate cancer at high risk of metabolic syndrome: randomized waitlist controlled trial","volume":"12","author":"Lee","journal-title":"JMIR Mhealth Uhealth"},{"issue":"12","key":"R3","doi-asserted-by":"publisher","first-page":"2108","DOI":"10.1002\/cncr.35241","article-title":"The Prostate Cancer Active Lifestyle Study (PALS): a randomized controlled trial of diet and exercise in overweight and obese men on active surveillance","volume":"130","author":"Wright","journal-title":"Cancer"},{"issue":"1","key":"R4","doi-asserted-by":"publisher","DOI":"10.1186\/s13063-024-07989-y","article-title":"Supported exercise TrAining for Men wIth prostate caNcer on Androgen deprivation therapy (STAMINA): study protocol for a randomised controlled trial of the clinical and cost-effectiveness of the STAMINA lifestyle intervention compared with optimised usual care, including internal pilot and parallel process evaluation","volume":"25","author":"McNaught","journal-title":"Trials"},{"issue":"9","key":"R5","doi-asserted-by":"publisher","first-page":"792","DOI":"10.1001\/jama.2023.14311","article-title":"Large language models answer medical questions accurately, but can\u2019t match clinicians\u2019 knowledge","volume":"330","author":"Harris","journal-title":"JAMA"},{"key":"R6","unstructured":"Wang C Long Q Xiao M et al. BioRAG: a RAG-LLM framework for biological question reasoning. arXiv. Preprint posted online on Aug 14, 2024. [doi: 10.48550\/arXiv.2408.01107]"},{"issue":"7","key":"R7","doi-asserted-by":"publisher","first-page":"549","DOI":"10.3390\/info16070549","article-title":"Large language models in medical chatbots: opportunities, challenges, and the need to address AI risks","volume":"16","author":"Chow","journal-title":"Information"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","DOI":"10.2196\/66633","article-title":"Developing effective frameworks for large language model-based medical chatbots: insights from radiotherapy education with ChatGPT","volume":"11","author":"Chow","journal-title":"JMIR Cancer"},{"issue":"1","key":"R9","doi-asserted-by":"publisher","DOI":"10.2196\/60063","article-title":"EyeGPT for patient inquiries and medical education: development and validation of an ophthalmology large language model","volume":"26","author":"Chen","journal-title":"J Med Internet Res"},{"issue":"3","key":"R10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2024.100943","article-title":"Can large language models reason about medical questions?","volume":"5","author":"Li\u00e9vin","journal-title":"Patterns (N Y)"},{"issue":"1","key":"R11","doi-asserted-by":"publisher","DOI":"10.1093\/pcmedi\/pbaf003","article-title":"Predictive model for daily risk alerts in sepsis patients in the ICU: visualization and clinical analysis of risk indicators","volume":"8","author":"Yang","journal-title":"Precis Clin Med"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.2196\/67201","article-title":"A knowledge-enhanced platform (MetaSepsisKnowHub) for retrieval augmented generation-based sepsis heterogeneity and personalized management: development study","volume":"27","author":"Zhang","journal-title":"J Med Internet Res"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01955-x","article-title":"Graph retrieval augmented large language models for facial phenotype associated rare genetic disease","volume":"8","author":"Song","journal-title":"NPJ Digit Med"},{"key":"R14","unstructured":"Yang A Xiao B Wang B et al. Baichuan 2: open large-scale language models. arXiv. Preprint posted online on Apr 17, 2025. [doi: 10.48550\/arXiv.2309.10305]"},{"key":"R15","doi-asserted-by":"crossref","unstructured":"Izacard G Grave E . Leveraging passage retrieval with generative models for open domain question answering. arXiv. Preprint posted online on Feb 3, 2021. [doi: 10.48550\/arXiv.2007.01282]","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"R16","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the middle: how language models use long contexts","volume":"12","author":"Liu","journal-title":"Trans Assoc Comput Linguist"},{"issue":"6","key":"R17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000877","article-title":"Retrieval augmented generation for large language models in healthcare: a systematic review","volume":"4","author":"Amugongo","journal-title":"PLoS Digit Health"},{"issue":"1","key":"R18","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/s44401-024-00004-1","article-title":"Retrieval-augmented generation for generative artificial intelligence in health care","volume":"2","author":"Yang","journal-title":"NPJ Health Syst"},{"key":"#cr-split#-R19.1","doi-asserted-by":"crossref","unstructured":"Wang Y Kordi Y Mishra S et al. Self-instruct: aligning language models with self-generated instructions. In: Rogers A Boyd-Graber J Okazaki N , editors. Presented at: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Jul 9-14, 2023:Association for Computational Linguistics. 13484-13508","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"#cr-split#-R19.2","doi-asserted-by":"crossref","unstructured":"Toronto, Canada. 2023.[doi: 10.18653\/v1\/2023.acl-long.754]","DOI":"10.18653\/v1\/2023.acl-long.754"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01356-6","article-title":"Autonomous medical evaluation for guideline adherence of large language models","volume":"7","author":"Fast","journal-title":"NPJ Digit Med"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-02005-2","article-title":"Evaluating clinical AI summaries with large language models as judges","volume":"8","author":"Croxford","journal-title":"NPJ Digit Med"},{"issue":"8","key":"R22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0325803","article-title":"Evaluation of large language models as a diagnostic tool for medical learners and clinicians using advanced prompting techniques","volume":"20","author":"Gaebe","journal-title":"PLoS One"},{"issue":"7972","key":"R23","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","journal-title":"Nature"},{"issue":"1","key":"R24","doi-asserted-by":"publisher","DOI":"10.2196\/69752","article-title":"Comparative evaluation of a medical large language model in answering real-world radiation oncology questions: multicenter observational study","volume":"27","author":"Dennst\u00e4dt","journal-title":"J Med Internet Res"},{"issue":"1","key":"R25","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01258-7","article-title":"A framework for human evaluation of large language models in healthcare derived from literature review","volume":"7","author":"Tam","journal-title":"NPJ Digit Med"},{"key":"R26","doi-asserted-by":"crossref","unstructured":"Zhang H Chen J Jiang F et al. HuatuoGPT, towards taming language model to be a doctor. In: Bouamor H Pino J Bali K , editors. Findings of the Association for Computational Linguistics: EMNLP 2023. Association for Computational Linguistics; 2023:10859-10885. [doi: 10.18653\/v1\/2023.findings-emnlp.725]","DOI":"10.18653\/v1\/2023.findings-emnlp.725"},{"key":"R27","unstructured":"Liu Z Wang P Li Y et al. RadOnc-GPT: a large language model for radiation oncology. arXiv. Preprint posted online on Nov 6, 2023. [doi: 10.48550\/arXiv.2309.10160]"},{"key":"R28","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2025.1611389","article-title":"LLM-as-a-Judge: automated evaluation of search query parsing using large language models","volume":"8","author":"Baysan","journal-title":"Front Big Data"},{"key":"R29","unstructured":"Chen N Hu Z Zou Q et al. JudgeLRM: large reasoning models as a judge. arXiv. Preprint posted online on Nov 3, 2025. [doi: 10.48550\/arXiv.2504.00050]"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Li D Jiang B Huang L et al. From generation to judgment: opportunities and challenges of LLM-as-a-judge. In: Christodoulopoulos C Chakraborty T Rose C Peng V , editors. The 2025 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics; 2025:2757-2791. [doi: 10.18653\/v1\/2025.emnlp-main.138]","DOI":"10.18653\/v1\/2025.emnlp-main.138"},{"key":"R31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.05685","article-title":"Judging LLM-as-a-Judge with MT-Bench and chatbot arena","author":"Zheng","journal-title":"arXiv"},{"issue":"1","key":"R32","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-06619-6","article-title":"A multi-dimensional performance evaluation of large language models in dental implantology: comparison of ChatGPT, DeepSeek, Grok, Gemini and Qwen across diverse clinical scenarios","volume":"25","author":"Wu","journal-title":"BMC Oral Health"},{"issue":"1","key":"R33","doi-asserted-by":"publisher","DOI":"10.2196\/75262","article-title":"Development and evaluation of a retrieval-augmented generation chatbot for orthopedic and trauma surgery patient education: mixed-methods study","volume":"4","author":"Baur","journal-title":"JMIR AI"},{"key":"R34","doi-asserted-by":"crossref","unstructured":"Haldar R Hockenmaier J . Rating roulette: self-inconsistency in LLM-as-a-judge frameworks. In: Christodoulopoulos C Chakraborty T Rose C Peng V , editors. Findings of the Association for Computational Linguistics. Association for Computational Linguistics; 2025:24986-25004. [doi: 10.18653\/v1\/2025.findings-emnlp.1361]","DOI":"10.18653\/v1\/2025.findings-emnlp.1361"},{"issue":"3","key":"R35","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","author":"Singhal","journal-title":"Nat Med"},{"issue":"2","key":"R36","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1162\/coli_a_00561","article-title":"LLM-based NLG evaluation: current status and challenges","volume":"51","author":"Gao","journal-title":"Comput Linguist"},{"issue":"3","key":"R37","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1016\/s0889-8529(02)00015-4","article-title":"What is evidence-based medicine?","volume":"31","author":"Montori","journal-title":"Endocrinol Metab Clin North Am"},{"issue":"8","key":"R38","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1016\/j.jacr.2006.12.007","article-title":"Evidence-based medicine","volume":"4","author":"Collins","journal-title":"J Am Coll Radiol"},{"issue":"7","key":"R39","doi-asserted-by":"publisher","DOI":"10.2196\/18599","article-title":"Role of artificial intelligence in patient safety outcomes: systematic literature review","volume":"8","author":"Choudhury","journal-title":"JMIR Med Inform"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2022-062158","article-title":"Barriers and enablers to implementing clinical practice guidelines in primary care: an overview of systematic reviews","volume":"13","author":"Wang","journal-title":"BMJ Open"},{"key":"R41","unstructured":"PCaPLMM_SFT: a prostate cancer patient lifestyle management model via supervised fine-tuning. Hugging Face. URL: https:\/\/huggingface.co\/RomilY\/PCaPLMM_SFT [Accessed 06-07-2026]"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e92663","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:23:53Z","timestamp":1785536633000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e92663"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":42,"URL":"https:\/\/doi.org\/10.2196\/92663","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"article-number":"v28i12e92663"}}