{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T03:20:16Z","timestamp":1767064816560,"version":"3.48.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T00:00:00Z","timestamp":1767052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Knowl Inf Syst"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1007\/s10115-025-02638-5","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T02:41:50Z","timestamp":1767062510000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing RAG-based LLMs for healthcare question answering tasks"],"prefix":"10.1007","volume":"68","author":[{"given":"Mukul","family":"Bedwa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishtha","family":"Hooda","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vikram","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,30]]},"reference":[{"issue":"9","key":"2638_CR1","doi-asserted-by":"publisher","first-page":"1248","DOI":"10.1093\/jamia\/ocy072","volume":"25","author":"L Laranjo","year":"2018","unstructured":"Laranjo L, Dunn AG, Tong HL et al (2018) Conversational agents in healthcare: a systematic review. J Am Med Inform Assoc 25(9):1248\u20131258. https:\/\/doi.org\/10.1093\/jamia\/ocy072","journal-title":"J Am Med Inform Assoc"},{"key":"2638_CR2","doi-asserted-by":"publisher","first-page":"e0212356","DOI":"10.1371\/journal.pone.0212356","volume":"14","author":"N Shahid","year":"2019","unstructured":"Shahid N, Rappon T, Berta W (2019) Applications of artificial neural networks in health care organizational decision-making: A scoping review. PLoS ONE 14:e0212356. https:\/\/doi.org\/10.1371\/journal.pone.0212356","journal-title":"PLoS ONE"},{"key":"2638_CR3","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/informatics11030057","volume":"11","author":"ZA Nazi","year":"2024","unstructured":"Nazi ZA, Peng W (2024) Large language models in healthcare and medical domain: a review. Informatics 11:57. https:\/\/doi.org\/10.3390\/informatics11030057","journal-title":"Informatics"},{"key":"2638_CR4","doi-asserted-by":"publisher","first-page":"9459","DOI":"10.48550\/arXiv.2005.11401","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A et al (2020) Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst 33:9459\u20139474. https:\/\/doi.org\/10.48550\/arXiv.2005.11401","journal-title":"Adv Neural Inf Process Syst"},{"key":"2638_CR5","doi-asserted-by":"publisher","first-page":"983","DOI":"10.3233\/SHTI240575","volume":"316","author":"K Kreimeyer","year":"2024","unstructured":"Kreimeyer K, Canzoniero JV, Fatteh M et al (2024) Using retrieval-augmented generation to capture molecularly-driven treatment relationships for precision oncology. Stud Health Technol Inform 316:983\u2013987. https:\/\/doi.org\/10.3233\/SHTI240575","journal-title":"Stud Health Technol Inform"},{"key":"2638_CR6","doi-asserted-by":"publisher","unstructured":"Karpukhin V, Oguz B, Min S et al (2020) Dense passage retrieval for open-domain question answering. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). Association for Computational Linguistics, pp 6769-6781. https:\/\/doi.org\/10.18653\/v1\/2020.emnlp-main.550","DOI":"10.18653\/v1\/2020.emnlp-main.550"},{"key":"2638_CR7","doi-asserted-by":"publisher","unstructured":"Zhao X, Liu S, Yang SY et al (2025) MedRAG: Enhancing retrieval-augmented generation with knowledge graph-elicited reasoning for healthcare copilot. In: Proceedings of the ACM Web Conference 2025. Association for Computing Machinery, pp 4442-4457. https:\/\/doi.org\/10.1145\/3696410.3714782","DOI":"10.1145\/3696410.3714782"},{"key":"2638_CR8","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1038\/s44401-024-00004-1","volume":"2","author":"R Yang","year":"2025","unstructured":"Yang R, Ning Y, Keppo E et al (2025) Retrieval-augmented generation for generative artificial intelligence in health care. NPJ Health Syst 2:2. https:\/\/doi.org\/10.1038\/s44401-024-00004-1","journal-title":"NPJ Health Syst"},{"key":"2638_CR9","doi-asserted-by":"publisher","unstructured":"Soudani H, Kanoulas E, Hasibi F (2024) Fine tuning vs. retrieval augmented generation for less popular knowledge. In: Proceedings of the 2024 ACM SIGIR Asia-Pacific Conference. Association for Computing Machinery, pp 12-22. https:\/\/doi.org\/10.1145\/3673791.3698415","DOI":"10.1145\/3673791.3698415"},{"key":"2638_CR10","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocaf008","author":"S Liu","year":"2025","unstructured":"Liu S, McCoy AB, Wright A et al (2025) Improving large language model applications in biomedicine with retrieval-augmented generation: A systematic review, meta-analysis, and clinical development guidelines. J Am Med Inform Assoc. https:\/\/doi.org\/10.1093\/jamia\/ocaf008","journal-title":"J Am Med Inform Assoc"},{"key":"2638_CR11","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1302\/2046-3758.73.BJR-2017-0147.R1","volume":"7","author":"LD Jones","year":"2018","unstructured":"Jones LD, Golan D, Hanna SA et al (2018) Artificial intelligence, machine learning and the evolution of healthcare. Bone Joint Res 7:223\u2013225. https:\/\/doi.org\/10.1302\/2046-3758.73.BJR-2017-0147.R1","journal-title":"Bone Joint Res"},{"key":"2638_CR12","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1007\/s10916-018-0965-7","volume":"42","author":"SM Anwar","year":"2018","unstructured":"Anwar SM, Majid M, Qayyum A et al (2018) Medical image analysis using convolutional neural networks: a review. J Med Syst 42:88. https:\/\/doi.org\/10.1007\/s10916-018-0965-7","journal-title":"J Med Syst"},{"key":"2638_CR13","doi-asserted-by":"publisher","unstructured":"Lipton ZC, Berkowitz J, Elkan C (2015) A critical review of recurrent neural networks for sequence learning. arXiv:1506.00019. https:\/\/doi.org\/10.48550\/arXiv.1506.00019","DOI":"10.48550\/arXiv.1506.00019"},{"key":"2638_CR14","doi-asserted-by":"publisher","unstructured":"Devlin J, Chang MW, Lee K et al (2019) BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT). Association for Computational Linguistics, pp 4171-4186. https:\/\/doi.org\/10.18653\/v1\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"key":"2638_CR15","doi-asserted-by":"publisher","unstructured":"Lewis M, Liu Y, Goyal N et al (2019) BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv:1910.13461. https:\/\/doi.org\/10.48550\/arXiv.1910.13461","DOI":"10.48550\/arXiv.1910.13461"},{"key":"2638_CR16","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.48550\/arXiv.2005.14165","volume":"33","author":"TB Brown","year":"2020","unstructured":"Brown TB, Mann B, Ryder N et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901. https:\/\/doi.org\/10.48550\/arXiv.2005.14165","journal-title":"Adv Neural Inf Process Syst"},{"key":"2638_CR17","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1038\/s41591-023-02229-1","volume":"29","author":"P Rajpurkar","year":"2023","unstructured":"Rajpurkar P, Topol EJ (2023) The risks and opportunities of large language models in medicine. Nat Med 29:377\u2013379. https:\/\/doi.org\/10.1038\/s41591-023-02229-1","journal-title":"Nat Med"},{"issue":"9","key":"2638_CR18","doi-asserted-by":"publisher","first-page":"1268","DOI":"10.3390\/healthcare11091268","volume":"11","author":"PN Ahmad","year":"2023","unstructured":"Ahmad PN, Shah AM, Lee K (2023) A review on electronic health record text-mining for biomedical name entity recognition in healthcare domain. Healthcare 11(9):1268. https:\/\/doi.org\/10.3390\/healthcare11091268","journal-title":"Healthcare"},{"key":"2638_CR19","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1609\/aaai.v39i1.30001","volume":"39","author":"M Ceresa","year":"2025","unstructured":"Ceresa M, Rossi A, Bianchi L et al (2025) RAGEv: a retrieval-augmented generation pipeline for healthcare QA. Proceed AAAI Conf Artificial Intell 39:1234\u20131245. https:\/\/doi.org\/10.1609\/aaai.v39i1.30001","journal-title":"Proceed AAAI Conf Artificial Intell"},{"key":"2638_CR20","doi-asserted-by":"publisher","unstructured":"Zhao X, Liu S, Yang S-Y, Miao C (2025) MedRAG: Enhancing Retrieval-augmented Generation with Knowledge Graph-Elicited Reasoning for Healthcare Copilot. In Proceedings of the ACM on Web Conference 2025 (WWW \u201925). Association for Computing Machinery, New York, NY, USA, 4442-4457. https:\/\/doi.org\/10.1145\/3696410.3714782","DOI":"10.1145\/3696410.3714782"},{"key":"2638_CR21","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1038\/s44222-024-00005-1","volume":"5","author":"X Wang","year":"2024","unstructured":"Wang X, Zhang Y, Lee J (2024) Retrieval-augmented generation in healthcare: opportunities and challenges. Nat Rev Bioinform 5:101\u2013110. https:\/\/doi.org\/10.1038\/s44222-024-00005-1","journal-title":"Nat Rev Bioinform"},{"key":"2638_CR22","doi-asserted-by":"publisher","unstructured":"Hsu H, Tzeng J (2025) DAT: Dynamic alpha tuning for hybrid retrieval in retrieval-augmented generation. arXiv:2503.23013. https:\/\/doi.org\/10.48550\/arXiv.2503.23013","DOI":"10.48550\/arXiv.2503.23013"},{"key":"2638_CR23","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","volume":"31","author":"K Singhal","year":"2025","unstructured":"Singhal K, Tu T, Gottweis J et al (2025) Toward expert-level medical question answering with large language models. Nat Med 31:943\u2013950. https:\/\/doi.org\/10.1038\/s41591-024-03423-7","journal-title":"Nat Med"},{"key":"2638_CR24","doi-asserted-by":"crossref","unstructured":"Labrak Y, Bazoge A, Morin E, Gourraud PA, Rouvier M, Dufour R (2024) Biomistral: A collection of open-source pretrained large language models for medical domains. arXiv preprint arXiv:2402.10373","DOI":"10.18653\/v1\/2024.findings-acl.348"},{"key":"2638_CR25","doi-asserted-by":"publisher","unstructured":"Zhu M, Ahuja A, Juan D-C, Wei W, Reddy CK (2020) Question Answering with Long Multiple-Span Answers. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 3840-3849, Online. Association for Computational Linguistics. https:\/\/doi.org\/10.18653\/v1\/2020.findings-emnlp.342","DOI":"10.18653\/v1\/2020.findings-emnlp.342"},{"key":"2638_CR26","unstructured":"Ben Abacha A, Demner-Fushman D (2019) MEDQUAD: Medical question answering dataset. https:\/\/github.com\/abachaa\/MEDQUAD"},{"key":"2638_CR27","unstructured":"Face H (2025) Health-QA-Finetune dataset. https:\/\/huggingface.co\/datasets\/medarsiddhant\/Health-QA-Finetune-Dataset"},{"key":"2638_CR28","doi-asserted-by":"publisher","first-page":"186","DOI":"10.4258\/hir.2013.19.3.186","volume":"19","author":"YJ Kim","year":"2013","unstructured":"Kim YJ, Oh Y, Park S et al (2013) Stratified sampling design based on data mining. Healthc Inform Res 19:186\u2013195. https:\/\/doi.org\/10.4258\/hir.2013.19.3.186","journal-title":"Healthc Inform Res"},{"key":"2638_CR29","doi-asserted-by":"publisher","unstructured":"Cuconasu F, Trappolini G, Siciliano F et al (2024) The power of noise: Redefining retrieval for RAG systems. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. Association for Computing Machinery, pp 719-729. https:\/\/doi.org\/10.1145\/3626772.3657821","DOI":"10.1145\/3626772.3657821"},{"key":"2638_CR30","doi-asserted-by":"publisher","unstructured":"Kamphuis C, de Vries AP, Boytsov L et al (2020) Which BM25 do you mean? A large-scale reproducibility study of scoring variants. In: Advances in Information Retrieval: 42nd European Conference on IR Research (ECIR 2020). Springer, pp 28-34. https:\/\/doi.org\/10.1007\/978-3-030-45442-5_4","DOI":"10.1007\/978-3-030-45442-5_4"},{"key":"2638_CR31","doi-asserted-by":"publisher","unstructured":"Nogueira R, Yang W, Cho K et al (2019) Multi-stage document ranking with BERT. arXiv:1910.14424. https:\/\/doi.org\/10.48550\/arXiv.1910.14424","DOI":"10.48550\/arXiv.1910.14424"},{"key":"2638_CR32","doi-asserted-by":"crossref","unstructured":"Jiang X, Yan L, Vavekanand R, Hu M (2023) Large Language Models in Healthcare Current Development and Future Directions. In Generative AI Research. https:\/\/hal.science\/hal-04643436v1","DOI":"10.20944\/preprints202407.0923.v1"},{"key":"2638_CR33","first-page":"1011","volume":"2024","author":"Y Shi","year":"2025","unstructured":"Shi Y, Xu S, Yang T, Liu Z, Liu T, Li X, Liu N (2025) MKRAG: medical knowledge retrieval augmented generation for medical question answering. AMIA Annu Symp Proc 2024:1011\u20131020","journal-title":"AMIA Annu Symp Proc"},{"key":"2638_CR34","doi-asserted-by":"publisher","unstructured":"Yu H, Gan A, Zhang K et al (2024) Evaluation of retrieval-augmented generation: A survey. In: Proceedings of the CCF Conference on Big Data. Chinese Computer Federation, pp 102-120. https:\/\/doi.org\/10.1007\/978-3-031-53443-7_10","DOI":"10.1007\/978-3-031-53443-7_10"}],"container-title":["Knowledge and Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-025-02638-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10115-025-02638-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10115-025-02638-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T02:41:55Z","timestamp":1767062515000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10115-025-02638-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["2638"],"URL":"https:\/\/doi.org\/10.1007\/s10115-025-02638-5","relation":{},"ISSN":["0219-1377","0219-3116"],"issn-type":[{"value":"0219-1377","type":"print"},{"value":"0219-3116","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]},"assertion":[{"value":"22 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 December 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"26"}}