{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T02:15:26Z","timestamp":1767579326144,"version":"3.48.0"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2024C01135"],"award-info":[{"award-number":["2024C01135"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LQ24F020007"],"award-info":[{"award-number":["LQ24F020007"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Health Inf Sci Syst"],"DOI":"10.1007\/s13755-025-00410-1","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T02:11:58Z","timestamp":1767579118000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical agent reflection for aligning LLM reasoning with clinical diagnostic processes"],"prefix":"10.1007","volume":"14","author":[{"given":"Xinda","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiaotong","family":"Li","sequence":"additional","affiliation":[]},{"given":"Deng","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Kehua","family":"Feng","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Keyan","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Huajun","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Wan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1636-5269","authenticated-orcid":false,"given":"Qiang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,5]]},"reference":[{"issue":"4","key":"410_CR1","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1097\/PTS.0000000000000338","volume":"15","author":"H Singh","year":"2019","unstructured":"Singh H, Graber ML, Hofer TP. Measures to improve diagnostic safety in clinical practice. J Patient Saf. 2019;15(4):311\u20136.","journal-title":"J Patient Saf"},{"key":"410_CR2","doi-asserted-by":"publisher","first-page":"59069","DOI":"10.2196\/59069","volume":"27","author":"K Zhang","year":"2025","unstructured":"Zhang K, Meng X, Yan X, Ji J, Liu J, Xu H, et al. Revolutionizing health care: the transformative impact of large language models in medicine. J Med Internet Res. 2025;27:59069.","journal-title":"J Med Internet Res"},{"key":"410_CR3","doi-asserted-by":"crossref","unstructured":"Buess L, Keicher M, Navab N, Maier A, Arasteh ST. From large language models to multimodal ai: A scoping review on the potential of generative ai in medicine. 2025. arXiv:2502.09242.","DOI":"10.1007\/s13534-025-00497-1"},{"key":"410_CR4","doi-asserted-by":"crossref","unstructured":"McDuff D, Schaekermann M, Tu T, Palepu A, Wang A, Garrison J, Singhal K, Sharma Y, Azizi S, Kulkarni K, et al. Towards accurate differential diagnosis with large language models. Nature. 2025;\u20137.","DOI":"10.1038\/s41586-025-08869-4"},{"issue":"4","key":"410_CR5","first-page":"337","volume":"11","author":"S Maleki Varnosfaderani","year":"2024","unstructured":"Maleki Varnosfaderani S, Forouzanfar M. The role of ai in hospitals and clinics: transforming healthcare in the 21st century. Bioeng. 2024;11(4):337.","journal-title":"Bioeng"},{"issue":"10","key":"410_CR6","doi-asserted-by":"publisher","first-page":"2440969","DOI":"10.1001\/jamanetworkopen.2024.40969","volume":"7","author":"E Goh","year":"2024","unstructured":"Goh E, Gallo R, Hom J, Strong E, Weng Y, Kerman H, et al. Large language model influence on diagnostic reasoning: a randomized clinical trial. JAMA Netw Open. 2024;7(10):2440969\u20132440969.","journal-title":"JAMA Netw Open"},{"key":"410_CR7","unstructured":"Brodeur PG, Buckley TA, Kanjee Z, Goh E, Ling EB, Jain P, Cabral S, Abdulnour R-E, Haimovich A, Freed JA, et al. Superhuman performance of a large language model on the reasoning tasks of a physician. 2024 arXiv:2412.10849."},{"key":"410_CR8","doi-asserted-by":"crossref","unstructured":"Almansoori M, Kumar K, Cholakkal H. Self-evolving multi-agent simulations for realistic clinical interactions. 2025. arXiv:2503.22678.","DOI":"10.1007\/978-3-032-05114-1_35"},{"issue":"8","key":"410_CR9","doi-asserted-by":"publisher","first-page":"030006052311627","DOI":"10.1177\/03000605231162798","volume":"51","author":"ZI Vally","year":"2023","unstructured":"Vally ZI, Khammissa RA, Feller G, Ballyram R, Beetge M, Feller L. Errors in clinical diagnosis: a narrative review. J Int Med Res. 2023;51(8):03000605231162798.","journal-title":"J Int Med Res"},{"key":"410_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-019-1426-2","volume":"17","author":"CJ Kelly","year":"2019","unstructured":"Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17:1\u20139.","journal-title":"BMC Med"},{"key":"410_CR11","doi-asserted-by":"crossref","unstructured":"Reese JT, Danis D, Caufield JH, Groza T, Casiraghi E, Valentini G, Mungall CJ, Robinson PN. On the limitations of large language models in clinical diagnosis. medRxiv, 2024;2023\u201307.","DOI":"10.1101\/2023.07.13.23292613"},{"issue":"9","key":"410_CR12","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","volume":"30","author":"P Hager","year":"2024","unstructured":"Hager P, Jungmann F, Holland R, Bhagat K, Hubrecht I, Knauer M, et al. Evaluation and mitigation of the limitations of large language models in clinical decision-making. Nat Med. 2024;30(9):2613\u201322.","journal-title":"Nat Med"},{"key":"410_CR13","unstructured":"Ball JR, Miller BT, Balogh EP. Improving diagnosis in health care. 2015."},{"issue":"3","key":"410_CR14","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1515\/dx-2018-0069","volume":"6","author":"M Vanstone","year":"2019","unstructured":"Vanstone M, Monteiro S, Colvin E, Norman G, Sherbino J, Sibbald M, et al. Experienced physician descriptions of intuition in clinical reasoning: a typology. Diagnosis. 2019;6(3):259\u201368.","journal-title":"Diagnosis"},{"issue":"5","key":"410_CR15","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1111\/jep.13549","volume":"27","author":"E Stolper","year":"2021","unstructured":"Stolper E, Van Royen P, Jack E, Uleman J, Olde RM. Embracing complexity with systems thinking in general practitioners\u2019 clinical reasoning helps handling uncertainty. J Eval Clin Pract. 2021;27(5):1175\u201381.","journal-title":"J Eval Clin Pract"},{"key":"410_CR16","doi-asserted-by":"crossref","unstructured":"Kwon T, Ong KT-i, Kang D, Moon S, Lee JR, Hwang D, Sohn B, Sim Y, Lee D, Yeo J. Large language models are clinical reasoners: Reasoning-aware diagnosis framework with prompt-generated rationales. In: Proc AAAI Conf Artif Intell, 38;18417\u201318425:2024.","DOI":"10.1609\/aaai.v38i16.29802"},{"key":"410_CR17","unstructured":"Wu J, Deng W, Li X, Liu S, Mi T, Peng Y, Xu Z, Liu Y, Cho H, Choi C-I, et al. Medreason: Eliciting factual medical reasoning steps in llms via knowledge graphs. 2025. arXiv:2504.00993."},{"key":"410_CR18","unstructured":"Fan Z, Liang C, Wu C, Zhang Y, Wang Y, Xie W. Chestx-reasoner: Advancing radiology foundation models with reasoning through step-by-step verification. 2025. arXiv:2504.20930."},{"issue":"1","key":"410_CR19","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1038\/s41746-024-01010-1","volume":"7","author":"T Savage","year":"2024","unstructured":"Savage T, Nayak A, Gallo R, Rangan E, Chen JH. Diagnostic reasoning prompts reveal the potential for large language model interpretability in medicine. NPJ Digital Medicine. 2024;7(1):20.","journal-title":"NPJ Digital Medicine"},{"key":"410_CR20","unstructured":"Wang G, Liu X. Medical large language model for diagnostic reasoning across specialties. NATURE PORTFOLIO HEIDELBERGER PLATZ 3, BERLIN, 14197, GERMANY. 2025."},{"key":"410_CR21","doi-asserted-by":"crossref","unstructured":"Wang B, Chang J, Qian Y, Chen G, Chen J, Jiang Z, Zhang J, Nakashima Y, Nagahara H. Direct: Diagnostic reasoning for clinical notes via large language models. 2024. arXiv:2408.01933.","DOI":"10.52202\/079017-2386"},{"issue":"7972","key":"410_CR22","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, et al. Large language models encode clinical knowledge. Nature. 2023;620(7972):172\u201380.","journal-title":"Nature"},{"issue":"8","key":"410_CR23","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"AJ Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu AJ, Ting DSJ, Elangovan K, Gutierrez L, Tan TF, Ting DSW. Large language models in medicine. Nat Med. 2023;29(8):1930\u201340.","journal-title":"Nat Med"},{"key":"410_CR24","unstructured":"Han T, Adams LC, Papaioannou J-M, Grundmann P, Oberhauser T, L\u00f6ser A, Truhn D, Bressem KK. Medalpaca\u2013an open-source collection of medical conversational ai models and training data. 2023. arXiv:2304.08247."},{"key":"410_CR25","unstructured":"Kim Y, Xu X, McDuff D, Breazeal C, Park HW. Health-llm: Large language models for health prediction via wearable sensor data. 2024. arXiv:2401.06866"},{"key":"410_CR26","unstructured":"Saab K, Tu T, Weng W-H, Tanno R, Stutz D, Wulczyn E, Zhang F, Strother T, Park C, Vedadi E, et al. Capabilities of gemini models in medicine. 2024. arXiv:2404.18416."},{"issue":"1","key":"410_CR27","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/s41698-024-00573-2","volume":"8","author":"D Truhn","year":"2024","unstructured":"Truhn D, Eckardt J-N, Ferber D, Kather JN. Large language models and multimodal foundation models for precision oncology. NPJ Precision Oncology. 2024;8(1):72.","journal-title":"NPJ Precision Oncology"},{"key":"410_CR28","unstructured":"Christophe C, Kanithi PK, Raha T, Khan S, Pimentel MA. Med42-v2: A suite of clinical llms. 2024. arXiv:2408.06142."},{"key":"410_CR29","unstructured":"Zhou H, Liu F, Gu B, Zou X, Huang J, Wu J, Li Y, Chen SS, Zhou P, Liu J, et al. A survey of large language models in medicine: Progress, application, and challenge. 2023. arXiv:2311.05112."},{"key":"410_CR30","unstructured":"Bolton E, Venigalla A, Yasunaga M, Hall D, Xiong B, Lee T, Daneshjou R, Frankle J, Liang P, Carbin M, et al. Biomedlm: A 2.7 b parameter language model trained on biomedical text. 2024. arXiv:2403.18421."},{"key":"410_CR31","doi-asserted-by":"crossref","unstructured":"Gao W, Deng Z, Niu Z, Rong F, Chen C, Gong Z, Zhang W, Xiao D, Li F, Cao Z, et al. Ophglm: Training an ophthalmology large language-and-vision assistant based on instructions and dialogue. 2023. arXiv:2306.12174.","DOI":"10.1016\/j.artmed.2024.103001"},{"key":"410_CR32","doi-asserted-by":"publisher","unstructured":"Peng C, Yang X, Chen A, Smith KE, PourNejatian N, Costa AB, et al. A study of generative large language model for medical research and healthcare. npj Dig Med. 2023;6(1):210. https:\/\/doi.org\/10.1038\/s41746-023-00958-w.","DOI":"10.1038\/s41746-023-00958-w"},{"key":"410_CR33","unstructured":"Yang L, Xu S, Sellergren A, Kohlberger T, Zhou Y, Ktena I, Kiraly A, Ahmed F, Hormozdiari F, Jaroensri T, et al. Advancing multimodal medical capabilities of gemini. 2024. arXiv:2405.03162."},{"key":"410_CR34","unstructured":"Singhal K, Tu T, Gottweis J, Sayres R, Wulczyn E, Amin M, Hou L, Clark K, Pfohl SR, Cole-Lewis H, et al. Toward expert-level medical question answering with large language models. Nature Medicine.2025;1\u20138."},{"key":"410_CR35","unstructured":"Chen J, Cai Z, Ji K, Wang X, Liu W, Wang R, Hou J, Wang B. Huatuogpt-o1, towards medical complex reasoning with llms. 2024. arXiv:2412.18925."},{"key":"410_CR36","first-page":"24824","volume":"35","author":"J Wei","year":"2022","unstructured":"Wei J, Wang X, Schuurmans D, Bosma M, Xia F, Chi E, et al. Chain-of-thought prompting elicits reasoning in large language models. Adv Neural Inf Process Syst. 2022;35:24824\u201337.","journal-title":"Adv Neural Inf Process Syst"},{"key":"410_CR37","first-page":"9459","volume":"33","author":"P Lewis","year":"2020","unstructured":"Lewis P, Perez E, Piktus A, Petroni F, Karpukhin V, Goyal N, et al. Retrieval-augmented generation for knowledge-intensive nlp tasks. Adv Neural Inf Process Syst. 2020;33:9459\u201374.","journal-title":"Adv Neural Inf Process Syst"},{"issue":"6","key":"410_CR38","doi-asserted-by":"publisher","first-page":"2300235","DOI":"10.1056\/AIcs2300235","volume":"1","author":"D Ferber","year":"2024","unstructured":"Ferber D, Wiest IC, W\u00f6lflein G, Ebert MP, Beutel G, Eckardt J-N, et al. Gpt-4 for information retrieval and comparison of medical oncology guidelines. NEJM AI. 2024;1(6):2300235.","journal-title":"NEJM AI"},{"key":"410_CR39","doi-asserted-by":"crossref","unstructured":"Xiong G, Jin Q, Lu Z, Zhang A. Benchmarking retrieval-augmented generation for medicine. 2024. arXiv:2402.13178.","DOI":"10.18653\/v1\/2024.findings-acl.372"},{"key":"410_CR40","doi-asserted-by":"crossref","unstructured":"Wu J, Zhu J, Qi Y, Chen J, Xu M, Menolascina F, Grau V. Medical graph rag: Towards safe medical large language model via graph retrieval-augmented generation. 2024. arXiv:2408.04187.","DOI":"10.18653\/v1\/2025.acl-long.1381"},{"key":"410_CR41","first-page":"51991","volume":"36","author":"G Li","year":"2023","unstructured":"Li G, Hammoud H, Itani H, Khizbullin D, Ghanem B. Camel: communicative agents for\u2019\u2019 mind\u2019\u2019 exploration of large language model society. Adv Neural Inf Process Syst. 2023;36:51991\u20132008.","journal-title":"Adv Neural Inf Process Syst"},{"key":"410_CR42","unstructured":"Wu Q, Bansal G, Zhang J, Wu Y, Li B, Zhu E, Jiang L, Zhang X, Zhang S, Liu J, et al. Autogen: Enabling next-gen llm applications via multi-agent conversation. 2023. arXiv:2308.08155"},{"key":"410_CR43","unstructured":"Huot F, Amplayo RK, Palomaki J, Jakobovits AS, Clark E, Lapata M. Agents\u2019 room: Narrative generation through multi-step collaboration. 2024. arXiv:2410.02603."},{"key":"410_CR44","unstructured":"Hong S, Zheng X, Chen J, Cheng Y, Wang J, Zhang C, Wang Z, Yau SKS, Lin Z, Zhou L, et al. Metagpt: Meta programming for multi-agent collaborative framework. 2023. arXiv:2308.00352."},{"key":"410_CR45","doi-asserted-by":"crossref","unstructured":"Han X, Wang N, Che S, Yang H, Zhang K, Xu SX. Enhancing investment analysis: Optimizing ai-agent collaboration in financial research. In: Proc 5th ACM Intl Conf AI in Finance.2024;538\u2013546.","DOI":"10.1145\/3677052.3698645"},{"key":"410_CR46","doi-asserted-by":"crossref","unstructured":"Zhang J, Xu X, Zhang N, Liu R, Hooi B, Deng S. Exploring collaboration mechanisms for llm agents: A social psychology view. 2023. arXiv:2310.02124.","DOI":"10.18653\/v1\/2024.acl-long.782"},{"key":"410_CR47","doi-asserted-by":"crossref","unstructured":"Tang X, Zou A, Zhang Z, Li Z, Zhao Y, Zhang X, Cohan A, Gerstein M. Medagents: Large language models as collaborators for zero-shot medical reasoning. 2023. arXiv:2311.10537.","DOI":"10.18653\/v1\/2024.findings-acl.33"},{"key":"410_CR48","unstructured":"Li J, Lai Y, Li W, Ren J, Zhang M, Kang X, Wang S, Li P, Zhang Y-Q, Ma W, et al. Agent hospital: A simulacrum of hospital with evolvable medical agents. 2024. arXiv:2405.02957."},{"key":"410_CR49","unstructured":"Kim Y, Park C, Jeong H, Chan YS, Xu X, McDuff D, Lee H, Ghassemi M, Breazeal C, Park HW. Mdagents: An adaptive collaboration of llms for medical decision-making. In: The Thirty-eighth Annual Conf Neural Inform Process Sys.2024."},{"key":"410_CR50","unstructured":"Standard QIG. Australian commission on safety and quality in health care. 2012."},{"issue":"1","key":"410_CR51","doi-asserted-by":"publisher","DOI":"10.1136\/bmjhci-2022-100699","volume":"30","author":"AW Demsash","year":"2023","unstructured":"Demsash AW, Kassie SY, Dubale AT, Chereka AA, Ngusie HS, Hunde MK, et al. Health professionals\u2019 routine practice documentation and its associated factors in a resource-limited setting: a cross-sectional study. BMJ health & care inform. 2023;30(1):100699.","journal-title":"BMJ health & care inform"},{"key":"410_CR52","doi-asserted-by":"crossref","unstructured":"Gale MS, Martin Gale B. Diagnosis: fundamental principles and methods. Cureus 2022;14(9).","DOI":"10.7759\/cureus.28730"},{"issue":"14","key":"410_CR53","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.3390\/app11146421","volume":"11","author":"D Jin","year":"2021","unstructured":"Jin D, Pan E, Oufattole N, Weng W-H, Fang H, Szolovits P. What disease does this patient have? a large-scale open domain question answering dataset from medical exams. Appl Sci. 2021;11(14):6421.","journal-title":"Appl Sci"},{"key":"410_CR54","unstructured":"Lyu S, Chi C, Cai H, Shi L, Yang X, Liu L, Chen X, Zhao D, Zhang Z, Lyu X, et al. Rjua-qa: A comprehensive qa dataset for urology. 2023. arXiv:2312.09785."},{"key":"410_CR55","unstructured":"Guo D, Yang D, Zhang H, Song J, Zhang R, Xu R, Zhu Q, Ma S, Wang P, Bi X, et al. Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning. 2025. arXiv:2501.12948."},{"key":"410_CR56","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang L, Wu J, Jiang X, Almeida D, Wainwright C, Mishkin P, et al. Training language models to follow instructions with human feedback. Adv Neural Inf Process Syst. 2022;35:27730\u201344.","journal-title":"Adv Neural Inf Process Syst"},{"key":"410_CR57","unstructured":"Zhou C, Liu P, Xu P, Iyer S, Sun J, Mao Y, Ma X, Efrat A, Yu P, Yu L, et al. Lima: Less is more for alignment. Adv Neural Inform Process Sys. 2024;36."},{"key":"410_CR58","doi-asserted-by":"crossref","unstructured":"Fan R-Z, Li X, Zou H, Li J, He S, Chern E, Hu J, Liu P. Reformatted alignment. 2024. arXiv:2402.12219.","DOI":"10.18653\/v1\/2024.findings-emnlp.32"},{"key":"410_CR59","doi-asserted-by":"crossref","unstructured":"Zheng Y, Zhang R, Zhang J, Ye Y, Luo Z, Feng Z, Ma Y. Llamafactory: Unified efficient fine-tuning of 100+ language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations). Association for Computational Linguistics, Bangkok, Thailand. 2024. arXiv: 2403.13372","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"410_CR60","unstructured":"Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W. Lora: Low-rank adaptation of large language models. 2021. arXiv:2106.09685."},{"key":"410_CR61","doi-asserted-by":"crossref","unstructured":"Rasley J, Rajbhandari S, Ruwase O, He Y. Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In: Proc 26th ACM SIGKDD Intl Conf Knowledge Discovery & Data Mining, 2020;3505\u20133506.","DOI":"10.1145\/3394486.3406703"},{"key":"410_CR62","doi-asserted-by":"crossref","unstructured":"Rajbhandari S, Rasley J, Ruwase O, He Y. Zero: Memory optimizations toward training trillion parameter models. In: SC20: Intl Conf High Perform Comput Networking, Storage and Anal, 2020;1\u201316. IEEE","DOI":"10.1109\/SC41405.2020.00024"},{"key":"410_CR63","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, Almeida D, Altenschmidt J, Altman S, Anadkat S, et al. Gpt-4 technical report. 2023. arXiv:2303.08774."},{"key":"410_CR64","unstructured":"Team Q. Qwen2.5: A Party of Foundation Models. 2024. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"410_CR65","unstructured":"Dubey A, Jauhri A, Pandey A, Kadian A, Al-Dahle A, Letman A, Mathur A, Schelten A, Yang A, Fan A, et al. The llama 3 herd of models. 2024. arXiv:2407.21783."},{"key":"410_CR66","unstructured":"DeepSeek-AI: DeepSeek-V3 Technical Report . 2025. https:\/\/arxiv.org\/abs\/2412.19437"},{"key":"410_CR67","unstructured":"Liu X, Liu H, Yang G, Jiang Z, Cui S, Zhang Z, Wang H, Tao L, Sun Y, Song Z, et al. A generalist medical language model for disease diagnosis assistance. Nature Med. 2025;1\u201311."},{"key":"410_CR68","unstructured":"Wang G, Gao M, Yang S, Zhang Y, He L, Huang L, Xiao H, Zhang Y, Li W, Chen L, et al. Citrus: Leveraging expert cognitive pathways in a medical language model for advanced medical decision support. 2025. arXiv:2502.18274."},{"key":"410_CR69","unstructured":"Wang B, Zhao H, Zhou H, Song L, Xu M, Cheng W, Zeng X, Zhang Y, Huo Y, Wang Z, et al. Baichuan-m1: Pushing the medical capability of large language models. 2025. arXiv:2502.12671."},{"key":"410_CR70","doi-asserted-by":"crossref","unstructured":"Chen H, Fang Z, Singla Y, Dredze M. Benchmarking large language models on answering and explaining challenging medical questions. 2024. arXiv:2402.18060.","DOI":"10.18653\/v1\/2025.naacl-long.182"},{"key":"410_CR71","unstructured":"OpenAI: Hello gpt-4o. OpenAI . 2024."}],"container-title":["Health Information Science and Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13755-025-00410-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13755-025-00410-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13755-025-00410-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T02:12:04Z","timestamp":1767579124000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13755-025-00410-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,5]]},"references-count":71,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["410"],"URL":"https:\/\/doi.org\/10.1007\/s13755-025-00410-1","relation":{},"ISSN":["2047-2501"],"issn-type":[{"value":"2047-2501","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,5]]},"assertion":[{"value":"1 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 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":"All authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"21"}}