{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T17:41:09Z","timestamp":1778866869791,"version":"3.51.4"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T00:00:00Z","timestamp":1721606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing","doi-asserted-by":"publisher","award":["L232033"],"award-info":[{"award-number":["L232033"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing-Tianjin-Hebei Basic Research Cooperation","award":["22JCZXJC00070"],"award-info":[{"award-number":["22JCZXJC00070"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82374302"],"award-info":[{"award-number":["82374302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82174533"],"award-info":[{"award-number":["82174533"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82204941"],"award-info":[{"award-number":["82204941"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2062"],"award-info":[{"award-number":["U23B2062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2023YFC3502604"],"award-info":[{"award-number":["2023YFC3502604"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"publisher","award":["2021YFC1712901"],"award-info":[{"award-number":["2021YFC1712901"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program Project of Ningxia Hui Autonomous Region","award":["2022BEG02036"],"award-info":[{"award-number":["2022BEG02036"]}]},{"DOI":"10.13039\/501100012151","name":"Sanming Project of Medicine in Shenzhen","doi-asserted-by":"publisher","award":["SZZYSM202311002"],"award-info":[{"award-number":["SZZYSM202311002"]}],"id":[{"id":"10.13039\/501100012151","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>The recent surge in large language models (LLMs) across various fields has yet to be fully realized in traditional Chinese medicine (TCM). This study aims to bridge this gap by developing a large language model tailored to TCM knowledge, enhancing its performance and accuracy in clinical reasoning tasks such as diagnosis, treatment, and prescription recommendations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>This study harnessed a wide array of TCM data resources, including TCM ancient books, textbooks, and clinical data, to create 3 key datasets: the TCM Pre-trained Dataset, the Traditional Chinese Patent Medicine (TCPM) Question Answering Dataset, and the Spleen and Stomach Herbal Prescription Recommendation Dataset. These datasets underpinned the development of the Lingdan Pre-trained LLM and 2 specialized models: the Lingdan-TCPM-Chat Model, which uses a Chain-of-Thought process for symptom analysis and TCPM recommendation, and a Lingdan Prescription Recommendation model (Lingdan-PR) that proposes herbal prescriptions based on electronic medical records.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The Lingdan-TCPM-Chat and the Lingdan-PR Model, fine-tuned on the Lingdan Pre-trained LLM, demonstrated state-of-the art performances for the tasks of TCM clinical knowledge answering and herbal prescription recommendation. Notably, Lingdan-PR outperformed all state-of-the-art baseline models, achieving an improvement of 18.39% in the Top@20 F1-score compared with the best baseline.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>This study marks a pivotal step in merging advanced LLMs with TCM, showcasing the potential of artificial intelligence to help improve clinical decision-making of medical diagnostics and treatment strategies. The success of the Lingdan Pre-trained LLM and its derivative models, Lingdan-TCPM-Chat and Lingdan-PR, not only revolutionizes TCM practices but also opens new avenues for the application of artificial intelligence in other specialized medical fields. Our project is available at https:\/\/github.com\/TCMAI-BJTU\/LingdanLLM.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocae087","type":"journal-article","created":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T23:19:50Z","timestamp":1721690390000},"page":"2019-2029","source":"Crossref","is-referenced-by-count":67,"title":["Lingdan: enhancing encoding of traditional Chinese medicine knowledge for clinical reasoning tasks with large language models"],"prefix":"10.1093","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6510-4367","authenticated-orcid":false,"given":"Rui","family":"Hua","sequence":"first","affiliation":[{"name":"Institute of Medical Intelligence, Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer Science & Technology, Beijing Jiaotong University , Beijing 100044, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1414-9354","authenticated-orcid":false,"given":"Xin","family":"Dong","sequence":"additional","affiliation":[{"name":"Institute of Medical Intelligence, Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer Science & Technology, Beijing Jiaotong University , Beijing 100044, China"}]},{"given":"Yu","family":"Wei","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Zixin","family":"Shu","sequence":"additional","affiliation":[{"name":"Institute of Medical Intelligence, Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer Science & Technology, Beijing Jiaotong University , Beijing 100044, China"}]},{"given":"Pengcheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Yunhui","family":"Hu","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Shuiping","family":"Zhou","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"He","family":"Sun","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Kaijing","family":"Yan","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Xijun","family":"Yan","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Kai","family":"Chang","sequence":"additional","affiliation":[{"name":"Institute of Medical Intelligence, Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer Science & Technology, Beijing Jiaotong University , Beijing 100044, China"}]},{"given":"Xiaodong","family":"Li","sequence":"additional","affiliation":[{"name":"Affiliated Hospital of Hubei University of Chinese Medicine , Wuhan 430065, China"},{"name":"Hubei Academy of Chinese Medicine , Wuhan 430061, China"},{"name":"Institute of Liver Diseases, Hubei Key Laboratory of Theoretical and Applied Research of Liver and Kidney in Traditional Chinese Medicine, Hubei Provincial Hospital of Traditional Chinese Medicine , Wuhan 430061, China"}]},{"given":"Yuning","family":"Bai","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Guang\u2019anmen Hospital, China Academy of Chinese Medical Sciences , Beijing 100053, China"}]},{"given":"Runshun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Guang\u2019anmen Hospital, China Academy of Chinese Medical Sciences , Beijing 100053, China"}]},{"given":"Wenjia","family":"Wang","sequence":"additional","affiliation":[{"name":"Innovation Center of Digital & Intelligent Chinese Medicine, Tasly Pharmaceutical Group Co., Ltd. , Tianjin 300410, China"}]},{"given":"Xuezhong","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of Medical Intelligence, Beijing Key Lab of Traffic Data Analysis and Mining, School of Computer Science & Technology, Beijing Jiaotong University , Beijing 100044, China"}]}],"member":"286","published-online":{"date-parts":[[2024,7,22]]},"reference":[{"key":"2024082207523389800_ocae087-B1","author":"OpenAI Team","year":"2022"},{"key":"2024082207523389800_ocae087-B2"},{"issue":"12","key":"2024082207523389800_ocae087-B3","doi-asserted-by":"crossref","first-page":"6074","DOI":"10.1109\/JBHI.2023.3316750","article-title":"Large AI models in health informatics: applications, challenges, and the future","volume":"27","author":"Qiu","year":"2023","journal-title":"IEEE J Biomed Health Inform"},{"key":"2024082207523389800_ocae087-B4","first-page":"1","article-title":"Unifying large language models and knowledge graphs: a roadmap","author":"Pan","year":"2024","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"4","key":"2024082207523389800_ocae087-B5","doi-asserted-by":"crossref","first-page":"e179","DOI":"10.1016\/S2589-7500(23)00048-1","article-title":"Using ChatGPT to write patient clinic letters","volume":"45","author":"Ali","year":"2023","journal-title":"Lancet Digit Health"},{"issue":"4","key":"2024082207523389800_ocae087-B6","doi-asserted-by":"crossref","first-page":"3378","DOI":"10.3390\/ijerph20043378","article-title":"Diagnostic accuracy of differential-diagnosis lists generated by generative pretrained transformer 3 chatbot for clinical vignettes with common chief complaints: A pilot study","volume":"20","author":"Hirosawa","year":"2023","journal-title":"IJERPH"},{"issue":"1","key":"2024082207523389800_ocae087-B7","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/s41746-023-00958-w","article-title":"A study of generative large language model for medical research and healthcare","volume":"6","author":"Peng","year":"2023","journal-title":"NPJ Digit Med"},{"issue":"1","key":"2024082207523389800_ocae087-B8","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","article-title":"Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios","volume":"47","author":"Cascella","year":"2023","journal-title":"J Med Syst"},{"issue":"6","key":"2024082207523389800_ocae087-B9","doi-asserted-by":"crossref","first-page":"696","DOI":"10.1016\/j.ajog.2023.03.009","article-title":"The exciting potential for ChatGPT in obstetrics and gynecology","volume":"228","author":"Gr\u00fcnebaum","year":"2023","journal-title":"Am J Obstet Gynecol"},{"key":"2024082207523389800_ocae087-B10","first-page":"1","article-title":"History and development of TCM case report in a real-world setting","volume":"2021","author":"Zeng","year":"2021","journal-title":"Evidence-Based Complement Altern Med"},{"issue":"7378","key":"2024082207523389800_ocae087-B11","doi-asserted-by":"crossref","first-page":"S82","DOI":"10.1038\/480S82a","article-title":"TCM: made in China","volume":"480","author":"Cheung","year":"2011","journal-title":"Nature"},{"key":"2024082207523389800_ocae087-B12","doi-asserted-by":"crossref","first-page":"104768","DOI":"10.1016\/j.phrs.2020.104768","article-title":"Traditional Chinese medicine for COVID-19 treatment","volume":"155","author":"Ren","year":"2020","journal-title":"Pharmacol Res"},{"issue":"2-3","key":"2024082207523389800_ocae087-B13","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.artmed.2009.07.012","article-title":"Development of traditional Chinese medicine clinical data warehouse for medical knowledge discovery and decision support","volume":"48","author":"Zhou","year":"2010","journal-title":"Artif Intell Med."},{"issue":"6","key":"2024082207523389800_ocae087-B14","doi-asserted-by":"crossref","first-page":"1007","DOI":"10.1109\/TKDE.2017.2787158","article-title":"A topic modeling approach for traditional chinese medicine prescriptions","volume":"30","author":"Yao","year":"2018","journal-title":"IEEE Trans Knowl Data Eng."},{"key":"2024082207523389800_ocae087-B15","first-page":"145","article-title":"Syndrome-aware herb recommendation with multi-graph convolution network","author":"Jin","year":"2020"},{"key":"2024082207523389800_ocae087-B16","doi-asserted-by":"crossref","first-page":"105752","DOI":"10.1016\/j.phrs.2021.105752","article-title":"FordNet: recommending traditional Chinese medicine formula via deep neural network integrating phenotype and molecule","volume":"173","author":"Zhou","year":"2021","journal-title":"Pharmacol Res."},{"key":"2024082207523389800_ocae087-B17","doi-asserted-by":"crossref","DOI":"10.1093\/jamia\/ocae066","article-title":"PresRecST: a novel herbal prescription recommendation algorithm for real-world patients with integration of syndrome differentiation and treatment planning","author":"Dong","year":"2024","journal-title":"J Am Med Inform Assoc."},{"key":"2024082207523389800_ocae087-B18","author":"Touvron","year":"2023"},{"key":"2024082207523389800_ocae087-B19","author":"Touvron","year":"2023"},{"key":"2024082207523389800_ocae087-B20","author":"Le Scao","year":"2022"},{"issue":"24(240","key":"2024082207523389800_ocae087-B21","first-page":"1","article-title":"PaLM: scaling language modeling with pathways","author":"Chowdhery","year":"2023","journal-title":"J Mach Learn Res"},{"key":"2024082207523389800_ocae087-B22","first-page":"10755","article-title":"Falcon-40B: an open large language model with state-of-the-art performance","volume":"2023","author":"Almazrouei","year":"2023","journal-title":"Findings Assoc Comput Linguist: ACL"},{"key":"2024082207523389800_ocae087-B23","author":"Yang","year":"2023"},{"key":"2024082207523389800_ocae087-B24","author":"Du"},{"key":"2024082207523389800_ocae087-B25","author":"Zeng","year":"2022"},{"key":"2024082207523389800_ocae087-B26","first-page":"7","author":"Sun","year":"2023"},{"key":"2024082207523389800_ocae087-B27","author":"Cui","year":"2023"},{"key":"2024082207523389800_ocae087-B28","author":"Zhang","year":"2022"},{"issue":"7972","key":"2024082207523389800_ocae087-B29","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"2024082207523389800_ocae087-B30","author":"Jin"},{"key":"2024082207523389800_ocae087-B31","author":"Hou","year":"2023"},{"issue":"6","key":"2024082207523389800_ocae087-B32","article-title":"ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge","volume":"15","author":"Li","year":"2023","journal-title":"Cureus"},{"key":"2024082207523389800_ocae087-B33","author":"Xiong","year":"2023"},{"key":"2024082207523389800_ocae087-B34","author":"Wang","year":"2023"},{"key":"2024082207523389800_ocae087-B35","first-page":"19368","author":"Yang"},{"key":"2024082207523389800_ocae087-B36","author":"Hu","year":"2021"},{"key":"2024082207523389800_ocae087-B37","author":"Sun","year":"2023"},{"key":"2024082207523389800_ocae087-B38","first-page":"36","article-title":"QLoRA: Efficient finetuning of quantized LLMs","author":"Dettmers","year":"2024","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024082207523389800_ocae087-B39","first-page":"1","author":"Rajbhandari","year":"2020"},{"key":"2024082207523389800_ocae087-B40","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv Neural Inform Process Syst"},{"key":"2024082207523389800_ocae087-B41","author":"Zhang","year":"2023"},{"key":"2024082207523389800_ocae087-B42","doi-asserted-by":"crossref","first-page":"5220","DOI":"10.1073\/pnas.0307760101","article-title":"Mixed-membership models of scientific publications","volume":"101(Suppl 1)","author":"Erosheva","year":"2004","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2024082207523389800_ocae087-B43","first-page":"450","author":"Balasubramanyan","year":"2011"},{"key":"2024082207523389800_ocae087-B44","first-page":"84","article-title":"Link-PLSA-LDA: a new unsupervised model for topics and influence of blogs","volume-title":"Proceedings of the International AAAI Conference on Web and Social Media","author":"Nallapati","year":"2008"},{"issue":"7","key":"2024082207523389800_ocae087-B45","doi-asserted-by":"crossref","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","article-title":"ML-KNN: a lazy learning approach to multi-label learning","volume":"40","author":"Zhang","year":"2007","journal-title":"Pattern Recognition"},{"key":"2024082207523389800_ocae087-B46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.neunet.2021.11.010","article-title":"Multi-layer information fusion based on graph convolutional network for knowledge-driven herb recommendation","volume":"146","author":"Yang","year":"2022","journal-title":"Neural Netw"},{"key":"2024082207523389800_ocae087-B47","first-page":"3776","author":"Dong","year":"2021"},{"key":"2024082207523389800_ocae087-B48","first-page":"378","author":"Wang","year":"2023"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/9\/2019\/58868322\/ocae087.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/31\/9\/2019\/58868322\/ocae087.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,22]],"date-time":"2024-08-22T13:27:12Z","timestamp":1724333232000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/31\/9\/2019\/7718082"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,22]]},"references-count":48,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2024,7,22]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocae087","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,7,22]]}}}