{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:33:59Z","timestamp":1792787639837,"version":"4.5.0"},"reference-count":29,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"the Medical Research Foundation of Putian University","award":["2024104"],"award-info":[{"award-number":["2024104"]}],"id":[{"id":"https:\/\/ror.org\/00jmsxk74","id-type":"ROR","asserted-by":"crossref"}]},{"name":"The Key Healthcare Projects of Putian","award":["2024SJYL043"],"award-info":[{"award-number":["2024SJYL043"]}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Science Progress"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:p>The exponential growth of biomedical literature poses significant challenges for knowledge management in specialized domains such as osteoporosis. While Large Language Models (LLMs) offer advanced natural language understanding capabilities, their direct application in high-risk medical contexts is hindered by hallucination risk, static knowledge, and limited traceability. This paper proposes a domain-specific Retrieval-Augmented Generation (RAG) system tailored for osteoporosis knowledge management, integrating authoritative sources from the International Osteoporosis Foundation and China\u2019s National Health Commission. The implemented system uses FAISS indexing with all-MiniLM-L6-v2 sentence embeddings and compares three retrieval strategies--Classic RAG, a fixed-budget non-agentic Multi-Query RAG (MQ-RAG), and Agentic RAG--against an LLM-only baseline. We evaluate the four conditions using a curated test set of 210 questions across true\/false, single-choice, and open-ended formats. Results from three representative LLMs--Deepseek-v3.2, ChatGPT-5, and Qwen3-max--are reported for objective accuracy and expert-rated answer quality. Inter-rater agreement for the open-ended expert evaluation was substantial (weighted Fleiss\u2019s kappa = 0.72). This work highlights the potential of agentic RAG architectures for specialized medical question-answering systems.<\/jats:p>","DOI":"10.1177\/00368504261489884","type":"journal-article","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T10:09:43Z","timestamp":1789639783000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["OsteoRAG: Retrieval-augmented generation for evidence-based osteoporosis knowledge management"],"prefix":"10.1177","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3125-3359","authenticated-orcid":false,"given":"Xiaoyu","family":"Xu","sequence":"first","affiliation":[{"name":"The Graduate School of Fujian Medical University"},{"name":"Affiliated Hospital of Putian University"},{"name":"Xiamen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianlin","family":"Shen","sequence":"additional","affiliation":[{"name":"The Graduate School of Fujian Medical University"},{"name":"Affiliated Hospital of Putian University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1093\/jbmr\/zjae131"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.21833\/ijaas.2024.03.017"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1002\/hpm.2303"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0957-4174(02)00083-0"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1177\/146045820100700102"},{"key":"e_1_3_3_7_2","first-page":"1194","article-title":"Merger of knowledge management and information technology in healthcare: Opportunities and challenges","volume":"2","author":"Dwivedi A","year":"2002","unstructured":"Dwivedi A, Bali RK, James AE, et al. Merger of knowledge management and information technology in healthcare: Opportunities and challenges. Canadian Conference on Electrical and Computer Engineering 2002; 2: 1194\u20131199.","journal-title":"Canadian Conference on Electrical and Computer Engineering"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-09138-0"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01670-7"},{"key":"e_1_3_3_10_2","doi-asserted-by":"crossref","unstructured":"He J Zhang B Rouhizadeh H et al. Retrieval-Augmented Generation in Biomedicine: A Survey of Technologies Datasets and Clinical Applications 2025 arXiv preprint arXiv:10.48550\/arXiv.2505.01146.","DOI":"10.21203\/rs.3.rs-8330917\/v1"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1386-5056(01)00167-8"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1111\/hir.12285"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12111219"},{"key":"e_1_3_3_14_2","unstructured":"Pambudi S Menolascina F. Bridging Clinical Narratives and ACR Appropriateness Guidelines: A Multi-Agent RAG System for Medical Imaging Decisions 2025 arXiv preprint arXiv:10.48550\/arXiv.2510.04969."},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12194-025-00941-y"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1108\/JKM-05-2020-0392"},{"issue":"2","key":"e_1_3_3_17_2","first-page":"ocaf008","article-title":"Systematic review and meta-analysis of retrieval-augmented generation in biomedical applications","volume":"32","author":"Liu S","year":"2025","unstructured":"Liu S, McCoy AB, Wright A, et al. Systematic review and meta-analysis of retrieval-augmented generation in biomedical applications. Journal of the American Medical Informatics Association 2025; 32(2): ocaf008.","journal-title":"Journal of the American Medical Informatics Association"},{"key":"e_1_3_3_18_2","first-page":"Q3","article-title":"Understanding the Barriers to Effective Bone Health Management in People With Multiple Sclerosis","volume":"27","author":"Grech LB","year":"2025","unstructured":"Grech LB, Jayanata LA, Caswell N, et al. Understanding the Barriers to Effective Bone Health Management in People With Multiple Sclerosis. International Journal of MS Care 2025; 27: Q3.","journal-title":"International Journal of MS Care"},{"key":"e_1_3_3_19_2","unstructured":"Bone Health & Osteoporosis Foundation. The clinician\u2019s guide to prevention and treatment of osteoporosis. 2022."},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2016.11.004"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-61520-670-4.ch023"},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1093\/jbmr\/zjae131"},{"issue":"1","key":"e_1_3_3_23_2","first-page":"6029","article-title":"Automatic Detection of Osteoporosis in Electronic Consultation (eConsult) Service Using Natural Language Processing","volume":"22","author":"Rahgozar A","year":"2024","unstructured":"Rahgozar A, Sethuram C, Goulet D, et al. Automatic Detection of Osteoporosis in Electronic Consultation (eConsult) Service Using Natural Language Processing. The Annals of Family Medicine 2024; 22(1): 6029.","journal-title":"The Annals of Family Medicine"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf008"},{"key":"e_1_3_3_25_2","first-page":"983","article-title":"Using Retrieval-Augmented Generation to Capture Molecularly-Driven Treatment Relationships for Precision Oncology","volume":"316","author":"Kreimeyer K","year":"2024","unstructured":"Kreimeyer K, Canzoniero JV, Fatteh M, et al. Using Retrieval-Augmented Generation to Capture Molecularly-Driven Treatment Relationships for Precision Oncology. Studies in Health Technology and Informatics 2024; 316: 983\u2013987. https:\/\/doi.org\/10.3233\/SHTI240575","journal-title":"Studies in Health Technology and Informatics"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.2196\/58041"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2024.104702"},{"key":"e_1_3_3_28_2","first-page":"248","article-title":"MedMCQA: A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering","volume":"174","author":"Pal A","year":"2022","unstructured":"Pal A, Umapathi LK, Sankarasubbu M, et al. MedMCQA: A Large-scale Multi-Subject Multi-Choice Dataset for Medical domain Question Answering. Proceedings of Machine Learning Research 2022; 174: 248\u2013260.","journal-title":"Proceedings of Machine Learning Research"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1259"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"}],"container-title":["Science Progress"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00368504261489884","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/00368504261489884","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/00368504261489884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T05:19:24Z","timestamp":1790745564000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/00368504261489884"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":29,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1177\/00368504261489884"],"URL":"https:\/\/doi.org\/10.1177\/00368504261489884","relation":{},"ISSN":["0036-8504","2047-7163"],"issn-type":[{"value":"0036-8504","type":"print"},{"value":"2047-7163","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"article-number":"00368504261489884"}}