{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T11:05:34Z","timestamp":1779793534586,"version":"3.53.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Science and Technology Counci","award":["(113-2634- F-002-002- , 113-2223-E-002 006- 113-2221-E-002-127-MY3)"],"award-info":[{"award-number":["(113-2634- F-002-002- , 113-2223-E-002 006- 113-2221-E-002-127-MY3)"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s10489-026-07186-1","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T12:39:24Z","timestamp":1775479164000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["KG-guided proactive questioning for LLMs in multi-turn interactive medical reasoning"],"prefix":"10.1007","volume":"56","author":[{"given":"Yu-Chen","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tzu-Ni","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6947-7646","authenticated-orcid":false,"given":"Li-Chen","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yung-Jen","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"issue":"7972","key":"7186_CR1","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","volume":"620","author":"K Singhal","year":"2023","unstructured":"Singhal K, Azizi S, Tu T, Mahdavi SS, Wei J, Chung HW, Scales N, Tanwani A, Cole-Lewis H, Pfohl S et al (2023) Large language models encode clinical knowledge. Nature 620(7972):172\u2013180","journal-title":"Nature"},{"key":"7186_CR2","doi-asserted-by":"crossref","unstructured":"Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, Amin M, Hou L, Clark K, Pfohl SR, Cole-Lewis H et al (2025) Toward expert-level medical question answering with large language models. Nat Med, 1\u20138","DOI":"10.1038\/s41591-024-03423-7"},{"key":"7186_CR3","doi-asserted-by":"crossref","unstructured":"Jin Q, Dhingra B, Liu Z, Cohen WW, Lu X (2019) Pubmedqa: a dataset for biomedical research question answering. arXiv:1909.06146","DOI":"10.18653\/v1\/D19-1259"},{"key":"7186_CR4","unstructured":"Pal A, Umapathi LK, Sankarasubbu M (2022) Medmcqa: a large-scale multi-subject multi-choice dataset for medical domain question answering. In: Conference on health, inference, and learning. PMLR, pp 248\u2013260"},{"key":"7186_CR5","unstructured":"Ball JR, Miller BT, Balogh EP (2015) Improving diagnosis in health care"},{"key":"7186_CR6","unstructured":"Dong B, Ni M, Huang Z, Yang G, Zuo W, Zhang L (2025) Mirage: assessing hallucination in multimodal reasoning chains of mllm. arXiv:2505.24238"},{"key":"7186_CR7","unstructured":"Orgad H, Toker M, Gekhman Z, Reichart R, Szpektor I, Kotek H, Belinkov Y (2024) Llms know more than they show: on the intrinsic representation of llm hallucinations. arXiv:2410.02707"},{"key":"7186_CR8","first-page":"28858","volume":"37","author":"S Li","year":"2024","unstructured":"Li S, Balachandran V, Feng S, Ilgen J, Pierson E, Koh PWW, Tsvetkov Y (2024) Mediq: question-asking llms and a benchmark for reliable interactive clinical reasoning. Adv Neural Inf Process Syst 37:28858\u201328888","journal-title":"Adv Neural Inf Process Syst"},{"key":"7186_CR9","unstructured":"Wu J, Deng W, Li X, Liu S, Mi T, Peng Y, Xu Z, Liu Y, Cho H, Choi C-I et al (2025) Medreason: eliciting factual medical reasoning steps in llms via knowledge graphs. arXiv:2504.00993"},{"key":"7186_CR10","unstructured":"Nori H, Lee YT, Zhang S, Carignan D, Edgar R, Fusi N, King N, Larson J, Li Y, Liu W et al (2023) Can generalist foundation models outcompete special-purpose tuning? case study in medicine. arXiv:2311.16452"},{"key":"7186_CR11","doi-asserted-by":"crossref","unstructured":"Wu J, Zhu J, Qi Y, Chen J, Xu M, Menolascina F, Grau V (2024) Medical graph rag: towards safe medical large language model via graph retrieval-augmented generation. arXiv:2408.04187","DOI":"10.18653\/v1\/2025.acl-long.1381"},{"key":"7186_CR12","doi-asserted-by":"crossref","unstructured":"Xu K, Cheng Y, Hou W, Tan Q, Li W (2024) Reasoning like a doctor: improving medical dialogue systems via diagnostic reasoning process alignment. arXiv:2406.13934","DOI":"10.18653\/v1\/2024.findings-acl.406"},{"key":"7186_CR13","doi-asserted-by":"crossref","unstructured":"Zuo K, Jiang Y, Mo F, Lio P (2025) Kg4diagnosis: a hierarchical multi-agent llm framework with knowledge graph enhancement for medical diagnosis. In: AAAI bridge program on AI for medicine and healthcare. PMLR, pp 195\u2013204","DOI":"10.1101\/2025.06.03.657521"},{"key":"7186_CR14","doi-asserted-by":"publisher","first-page":"58670","DOI":"10.2196\/58670","volume":"4","author":"Y Gao","year":"2025","unstructured":"Gao Y, Li R, Croxford E, Caskey J, Patterson BW, Churpek M, Miller T, Dligach D, Afshar M (2025) Leveraging medical knowledge graphs into large language models for diagnosis prediction: design and application study. Jmir Ai 4:58670","journal-title":"Jmir Ai"},{"key":"7186_CR15","doi-asserted-by":"crossref","unstructured":"Neumann M, King D, Beltagy I, Ammar W (2019) Scispacy: fast and robust models for biomedical natural language processing. arXiv:1902.07669","DOI":"10.18653\/v1\/W19-5034"},{"key":"7186_CR16","doi-asserted-by":"crossref","unstructured":"Liu F, Shareghi E, Meng Z, Basaldella M, Collier N (2020) Self-alignment pretraining for biomedical entity representations. arXiv:2010.11784","DOI":"10.18653\/v1\/2021.naacl-main.334"},{"key":"7186_CR17","doi-asserted-by":"crossref","unstructured":"Wang K, Shen W, Yang Y, Quan X, Wang R (2020) Relational graph attention network for aspect-based sentiment analysis. arXiv:2004.12362","DOI":"10.18653\/v1\/2020.acl-main.295"},{"key":"7186_CR18","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. In: Proceedings of the IEEE international conference on computer vision, pp 2980\u20132988","DOI":"10.1109\/ICCV.2017.324"},{"key":"7186_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12911-016-0369-1","volume":"16","author":"D Hausmann","year":"2016","unstructured":"Hausmann D, Zulian C, Battegay E, Zimmerli L (2016) Tracing the decision-making process of physicians with a decision process matrix. BMC Med Inform Decis Mak 16:1\u201311","journal-title":"BMC Med Inform Decis Mak"},{"key":"7186_CR20","doi-asserted-by":"crossref","unstructured":"Bodenreider O (2004) The unified medical language system (umls): integrating biomedical terminology. Nucleic Acids Res 32(suppl_1):267\u2013270","DOI":"10.1093\/nar\/gkh061"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07186-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-026-07186-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-026-07186-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T10:47:40Z","timestamp":1779792460000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-026-07186-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":20,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["7186"],"URL":"https:\/\/doi.org\/10.1007\/s10489-026-07186-1","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"19 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 April 2026","order":3,"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 conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of Interest"}},{"value":"The gathering of experimental data from human subjects has been sanctioned by the NTUH Research Ethics Committee B, under ethics board protocol number 202105013RINB, as of June 18, 2021. Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All participants provided consent for the publication of anonymized data.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"187"}}