{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T18:17:25Z","timestamp":1778782645577,"version":"3.51.4"},"reference-count":45,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["25JS2830402"],"award-info":[{"award-number":["25JS2830402"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["2025SHZDZX025G06"],"award-info":[{"award-number":["2025SHZDZX025G06"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2025ZD0123402"],"award-info":[{"award-number":["2025ZD0123402"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.eswa.2026.132267","type":"journal-article","created":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T23:55:47Z","timestamp":1775260547000},"page":"132267","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Benchmarking large language models for end-to-end clinical support in traditional chinese medicine"],"prefix":"10.1016","volume":"325","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2059-5491","authenticated-orcid":false,"given":"Dongsheng","family":"Shi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9646-1468","authenticated-orcid":false,"given":"Xin","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5509-2103","authenticated-orcid":false,"given":"Yue","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-7560","authenticated-orcid":false,"given":"Linlin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"12","key":"10.1016\/j.eswa.2026.132267_bib0001","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1002\/j.0022-0337.2008.72.12.tb04620.x","article-title":"Assessing dental students\u2019 competence: Best practice recommendations in the performance assessment literature and investigation of current practices in predoctoral dental education","volume":"72","author":"Albino","year":"2008","journal-title":"Journal of Dental Education"},{"issue":"4","key":"10.1016\/j.eswa.2026.132267_sbref0002","first-page":"517","article-title":"Differential diagnosis. prescriptive teaching: A critical appraisal","volume":"49","author":"Arter","year":"1979","journal-title":"Review of Educational Research"},{"key":"10.1016\/j.eswa.2026.132267_bib0003","doi-asserted-by":"crossref","unstructured":"Bhatti, A. (2018). Cognitive bias in clinical practice – nurturing healthy skepticism among medical students. Volume 9, 235\u2013237. https:\/\/www.dovepress.com\/cognitive-bias-in-clinical-practice-nurturing-healthy-skepticism-among-peer-reviewed-article-AMEP. 10.2147\/AMEP.S149558.","DOI":"10.2147\/AMEP.S149558"},{"key":"10.1016\/j.eswa.2026.132267_bib0004","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"17709","article-title":"MedBench: A large-scale chinese benchmark for evaluating medical large language models","volume":"vol. 38","author":"Cai","year":"2024"},{"issue":"2","key":"10.1016\/j.eswa.2026.132267_bib0005","doi-asserted-by":"crossref","first-page":"681","DOI":"10.21037\/tcr-20-2596","article-title":"A network pharmacology approach for investigating the multi-target mechanisms of huangqi in the treatment of colorectal cancer","volume":"10","author":"Chu","year":"2021","journal-title":"Translational Cancer Research"},{"key":"10.1016\/j.eswa.2026.132267_bib0006","unstructured":"Del\u00e9tang, G., Ruoss, A., Duquenne, P.-A., Catt, E., Genewein, T., Mattern, C., Grau-Moya, J., Wenliang, L. K., Aitchison, M., Orseau, L. et al. (2023). Language modeling is compression. arXiv preprint arXiv: 2309.10668."},{"issue":"1","key":"10.1016\/j.eswa.2026.132267_bib0007","article-title":"Study on traditional chinese medicine syndromes and syndrome elements in non-alcoholic fatty liver disease","volume":"37","author":"Gaiya","year":"2021","journal-title":"Journal of Clinical Hepatology"},{"issue":"43","key":"10.1016\/j.eswa.2026.132267_bib0008","doi-asserted-by":"crossref","DOI":"10.1126\/sciadv.adh0215","article-title":"Network medicine framework reveals generic herb-symptom effectiveness of traditional chinese medicine","volume":"9","author":"Gan","year":"2023","journal-title":"Science Advances"},{"key":"10.1016\/j.eswa.2026.132267_sbref0009","series-title":"The twelfth international conference on learning representations","article-title":"CRITIC: Large language models can self-correct with tool-interactive critiquing","author":"Gou","year":"2024"},{"issue":"13","key":"10.1016\/j.eswa.2026.132267_bib0010","doi-asserted-by":"crossref","first-page":"1493","DOI":"10.1001\/archinte.165.13.1493","article-title":"Diagnostic error in internal medicine","volume":"165","author":"Graber","year":"2005","journal-title":"Archives of Internal Medicine"},{"key":"10.1016\/j.eswa.2026.132267_bib0011","doi-asserted-by":"crossref","DOI":"10.3389\/fcell.2021.778826","article-title":"Exploring the mechanism of action of canmei formula against colorectal adenoma through multi-omics technique","volume":"9","author":"Guo","year":"2021","journal-title":"Frontiers in Cell and Developmental Biology"},{"issue":"4","key":"10.1016\/j.eswa.2026.132267_bib0012","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.dcmed.2025.01.007","article-title":"TCMLLM-PR: Evaluation of large language models for prescription recommendation in traditional chinese medicine","volume":"7","author":"Haoyu","year":"2024","journal-title":"Digital Chinese Medicine"},{"issue":"21","key":"10.1016\/j.eswa.2026.132267_bib0013","first-page":"2210","article-title":"Cognitive understanding and exploration of traditional chinese medicine syndromes in irritable bowel syndrome","volume":"18","author":"Hongbing","year":"2010","journal-title":"World Journal of Gastroenterology"},{"key":"10.1016\/j.eswa.2026.132267_bib0014","doi-asserted-by":"crossref","DOI":"10.3389\/fphar.2020.582520","article-title":"A systematic study of mechanism of sargentodoxa cuneata and patrinia scabiosifolia against pelvic inflammatory disease with dampness-heat stasis syndrome via network pharmacology approach","volume":"11","author":"Hu","year":"2020","journal-title":"Frontiers in Pharmacology"},{"issue":"14","key":"10.1016\/j.eswa.2026.132267_bib0015","doi-asserted-by":"crossref","first-page":"6421","DOI":"10.3390\/app11146421","article-title":"What disease does this patient have? A large-scale open domain question answering dataset from medical exams","volume":"11","author":"Jin","year":"2021","journal-title":"Applied Sciences"},{"key":"10.1016\/j.eswa.2026.132267_bib0016","unstructured":"Kang, Y., Chang, Y., Fu, J., Wang, Y., Wang, H., & Zhang, W. (2023). CMLM-Zhongjing: Large language model is good story listener. https:\/\/github.com\/pariskang\/CMLM-ZhongJing."},{"issue":"4","key":"10.1016\/j.eswa.2026.132267_sbref0017","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1016\/0002-9343(89)90342-2","article-title":"Cognitive errors in diagnosis: Instantiation, classification, and consequences","volume":"86","author":"Kassirer","year":"1989","journal-title":"The American Journal of Medicine"},{"key":"10.1016\/j.eswa.2026.132267_bib0018","unstructured":"Lei, F., Liu, Q., Huang, Y., He, S., Zhao, J., & Liu, K. (2023). S3Eval: A synthetic, scalable, systematic evaluation suite for large language models. arXiv preprint arXiv: 2310.15147."},{"key":"10.1016\/j.eswa.2026.132267_bib0019","series-title":"Proceedings of the 2021 conference on empirical methods in natural language processing","first-page":"8862","article-title":"MLEC-QA: A chinese multi-choice biomedical question answering dataset","author":"Li","year":"2021"},{"issue":"5","key":"10.1016\/j.eswa.2026.132267_bib0020","doi-asserted-by":"crossref","first-page":"888","DOI":"10.1016\/j.eng.2019.01.015","article-title":"Quality markers of traditional chinese medicine: concept, progress, and perspective","volume":"5","author":"Li","year":"2019","journal-title":"Engineering"},{"key":"10.1016\/j.eswa.2026.132267_bib0021","first-page":"52430","article-title":"Benchmarking large language models on cmexam-a comprehensive chinese medical exam dataset","volume":"36","author":"Liu","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"9","key":"10.1016\/j.eswa.2026.132267_bib0022","doi-asserted-by":"crossref","first-page":"S63","DOI":"10.1097\/00001888-199009000-00045","article-title":"The assessment of clinical skills\/competence\/performance","volume":"65","author":"Miller","year":"1990","journal-title":"Academic Medicine"},{"issue":"06","key":"10.1016\/j.eswa.2026.132267_bib0023","first-page":"691","article-title":"Analysis of literature on TCM syndromes and syndrome elements in chronic fatigue syndrome","volume":"34","author":"Min","year":"2014","journal-title":"Chinese Journal of Integrated Traditional and Western Medicine"},{"key":"10.1016\/j.eswa.2026.132267_bib0024","doi-asserted-by":"crossref","unstructured":"Nendaz, M., & Perrier, A. (2012). Diagnostic errors and flaws in clinical reasoning: mechanisms and prevention in practice. Swiss medical weekly, 142 (4344) w13706--w13706.https:\/\/smw.ch\/index.php\/smw\/article\/view\/1609. 10.4414\/smw.2012.13706.","DOI":"10.4414\/smw.2012.13706"},{"issue":"7392","key":"10.1016\/j.eswa.2026.132267_bib0025","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1136\/bmj.326.7392.753","article-title":"Work based assessment","volume":"326","author":"Norcini","year":"2003","journal-title":"BMJ"},{"key":"10.1016\/j.eswa.2026.132267_bib0026","doi-asserted-by":"crossref","unstructured":"Norman, G. R., Monteiro, S. D., Sherbino, J., Ilgen, J. S., Schmidt, H. G., & Mamede, S. (2017). The causes of errors in clinical reasoning: Cognitive biases, knowledge deficits, and dual process thinking. 92(1), 23\u201330. Place: United States. 10.1097\/ACM.0000000000001421.","DOI":"10.1097\/ACM.0000000000001421"},{"key":"10.1016\/j.eswa.2026.132267_bib0027","doi-asserted-by":"crossref","unstructured":"Ouyang, Z., Qiu, Y., Wang, L., De Melo, G., Zhang, Y., Wang, Y., & He, L. (2024). CliMedBench: A large-scale chinese benchmark for evaluating medical large language models in clinical scenarios. arXiv preprint arXiv: 2410.03502.","DOI":"10.18653\/v1\/2024.emnlp-main.480"},{"key":"10.1016\/j.eswa.2026.132267_bib0028","series-title":"Conference on health, inference, and learning","first-page":"248","article-title":"MedMCQA: A large-scale multi-subject multi-choice dataset for medical domain question answering","author":"Pal","year":"2022"},{"key":"10.1016\/j.eswa.2026.132267_bib0029","doi-asserted-by":"crossref","unstructured":"Pampari, A., Raghavan, P., Liang, J., & Peng, J. (2018). EMRQA: A large corpus for question answering on electronic medical records. arXiv preprint arXiv: 1809.00732.","DOI":"10.18653\/v1\/D18-1258"},{"key":"10.1016\/j.eswa.2026.132267_bib0030","doi-asserted-by":"crossref","DOI":"10.1016\/j.phymed.2021.153911","article-title":"An image-based fingerprint-efficacy screening strategy for uncovering active compounds with interactive effects in yindan xinnaotong soft capsule","volume":"96","author":"Pang","year":"2022","journal-title":"Phytomedicine"},{"key":"10.1016\/j.eswa.2026.132267_bib0031","doi-asserted-by":"crossref","unstructured":"Singhal, K., Azizi, S., Tu, T., Mahdavi, S. S., Wei, J., Chung, H. W., Scales, N., Tanwani, A., Cole-Lewis, H., Pfohl, S., Payne, P., Seneviratne, M., Gamble, P., Kelly, C., Babiker, A., Sch\u00e4rli, N., Chowdhery, A., Mansfield, P., Demner-Fushman, D., Ag\u00fcera y Arcas, B., Webster, D., Corrado, G. S., Matias, Y., Chou, K., Gottweis, J., Tomasev, N., Liu, Y., Rajkomar, A., Barral, J., Semturs, C., Karthikesalingam, A., & Natarajan, V. Large language models encode clinical knowledge. 620(7972), 172\u2013180. 10.1038\/s41586-023-06291-2.","DOI":"10.1038\/s41586-023-06291-2"},{"key":"10.1016\/j.eswa.2026.132267_sbref0032","series-title":"Proceedings of the 2023 conference on empirical methods in natural language processing: Industry track","first-page":"650","article-title":"Self-criticism: Aligning large language models with their understanding of helpfulness, honesty, and harmlessness","author":"Tan","year":"2023"},{"key":"10.1016\/j.eswa.2026.132267_bib0033","unstructured":"Wang, S., Long, Z., Fan, Z., Wei, Z., & Huang, X. (2024a). Benchmark self-evolving: A multi-agent framework for dynamic llm evaluation. arXiv preprint arXiv: 2402.11443."},{"key":"10.1016\/j.eswa.2026.132267_bib0034","article-title":"CMB: A comprehensive medical benchmark in chinese. arxiv","volume":"4","author":"Wang","year":"2024","journal-title":"Preprint posted online on April"},{"issue":"1","key":"10.1016\/j.eswa.2026.132267_bib0035","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1038\/s41597-025-04772-9","article-title":"TCMEval-SDT: A benchmark dataset for syndrome differentiation thought of traditional chinese medicine","volume":"12","author":"Wang","year":"2025","journal-title":"Scientific Data"},{"key":"10.1016\/j.eswa.2026.132267_bib0036","first-page":"558","article-title":"Analysis of traditional chinese medicine syndromes and symptom distribution patterns in polycystic ovary syndrome in Jiangsu region","volume":"10","author":"Yu","year":"2021","journal-title":"Traditional Chinese Medicine"},{"key":"10.1016\/j.eswa.2026.132267_bib0037","doi-asserted-by":"crossref","unstructured":"Yu, X., Cheng, H., Liu, X., Roth, D., & Gao, J. (2023). ReEval: Automatic hallucination evaluation for retrieval-augmented large language models via transferable adversarial attacks. arXiv preprint arXiv: 2310.12516.","DOI":"10.18653\/v1\/2024.findings-naacl.85"},{"key":"10.1016\/j.eswa.2026.132267_bib0038","unstructured":"Yue, W., Wang, X., Zhu, W., Guan, M., Zheng, H., Wang, P., Sun, C., & Ma, X. (2024). TCMBench: A comprehensive benchmark for evaluating large language models in traditional chinese medicine. arXiv preprint arXiv: 2406.01126."},{"issue":"1","key":"10.1016\/j.eswa.2026.132267_bib0039","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1186\/s13020-024-01056-z","article-title":"Network pharmacology: a crucial approach in traditional chinese medicine research","volume":"20","author":"Zhai","year":"2025","journal-title":"Chinese Medicine"},{"issue":"1","key":"10.1016\/j.eswa.2026.132267_bib0040","article-title":"Network pharmacology: A new approach for chinese herbal medicine research","volume":"2013","author":"Zhang","year":"2013","journal-title":"Evidence-Based Complementary and Alternative Medicine"},{"key":"10.1016\/j.eswa.2026.132267_bib0041","first-page":"135904","article-title":"DARG: Dynamic evaluation of large language models via adaptive reasoning graph","volume":"37","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.eswa.2026.132267_bib0042","unstructured":"Zhu, K., Chen, J., Wang, J., Gong, N. Z., Yang, D., & Xie, X. (2023a). DYVAL: Dynamic evaluation of large language models for reasoning tasks. arXiv preprint arXiv: 2309.17167."},{"key":"10.1016\/j.eswa.2026.132267_bib0043","unstructured":"Zhu, K., Wang, J., Zhao, Q., Xu, R., & Xie, X. (2024). Dynamic evaluation of large language models by meta probing agents. arXiv preprint arXiv: 2402.14865."},{"key":"10.1016\/j.eswa.2026.132267_bib0044","first-page":"2023","article-title":"ChatMed: A chinese medical large language model","volume":"18","author":"Zhu","year":"2023","journal-title":"Retrieved September"},{"key":"10.1016\/j.eswa.2026.132267_bib0045","article-title":"Shennong-TCM: A traditional chinese medicine large language model","author":"Zhu","year":"2023","journal-title":"GitHub"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011802?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0957417426011802?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T17:52:54Z","timestamp":1778781174000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0957417426011802"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":45,"alternative-id":["S0957417426011802"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132267","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Benchmarking large language models for end-to-end clinical support in traditional chinese medicine","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.132267","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"132267"}}