Construction and application of the “Huaxi Hongyi” large medical model_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

ZHENG Bing , YANG Hao , YANG Xuchen , WANG Zhenwu , LIU Dongfeng ,  SHI Rui

Department of Information, West China Hospital of Sichuan University, Chengdu, 610041, P. R. China;

Corresponding author：

SHI Rui, Email: dr.shirui@hotmail.com

Keywords：

Large language model; data annotation; multimodal learning; medical record generation; articficial intelligence

DOI：

10.7507/1007-4848.202503081

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective This article takes the construction of the Huaxi Hongyi Medical University model as the core, explores its application effect in assisting the generation of medical records, and provides a practical path for the construction and application of artificial intelligence in medical institutions. Methods Through strategies such as multimodal data fusion, domain adaptation training, and localization of hardware adaptation, a large-scale medical model with 72 billion parameters was constructed. Combined with technologies such as speech recognition, knowledge graphs, and reinforcement learning, an application system for assisting in the generation of medical records was developed. Results Taking the assisted generation of discharge records as an example, in the pilot department, the average completion time of writing was reduced from 21 minutes to 5 minutes (a decrease of 76.2%), the accuracy rate of the model output reached 92.4%, and the annotation consistency Kappa coefficient was 0.85. Conclusion The model of medical institutions constructing independently controllable large-scale medical models and incubating various applications based on them can provide a reference path for the artificial intelligence construction of similar institutions.

1.	张霄. 三部门联合印发《卫生健康行业人工智能应用场景参考指引》. 中医药管理杂志, 2024, 32(22): 35.Zhang X. Three departments jointly issued "the reference duide for AI application scenarios in the healthcare industry". J Trad Chin Med Manag, 2024, 32(22): 35.
2.	国家发展改革委. 国家发展改革委商务部关于《鼓励外商投资产业目录(2020年版)(征求意见稿)》公开征求意见的通知. 中国对外经济贸易文告, 2020, 54: 10-27.National Development and Reform Commission. Notice on Public Solicitation of Opinions on the “Catalog of Industries Encouraging Foreign Investment (2020 Edition) (Draft for Comments)” by the National Development and Reform Commission and the Ministry of Commerce. China Foreign Trade and Economic Cooperation Gazette, 2020, 54: 10-27.
3.	中共中央国务院印发《数字中国建设整体布局规划》. 人民日报, 2023-02-28.001). The Central Committee of the Communist Party of China and the State Council issued the "Overall Layout Plan for Digital China Construction". People's Daily, 2023-02-28 (001).
4.	王春晖. 《数字中国建设整体布局规划》的深入解读. 通信世界, 2023, 5: 4-5.Wang CH. Interpretation of the “overall layout plan for digital China construction”. Commun World, 2023, 5: 4-5.
5.	国务院办公厅关于推动公立医院高质量发展的意见. 中华人民共和国国务院公报, 2021, 17: 174-178.Opinions of the General Office of the State Council on promoting the high-quality development of public hospitals. Gazette of the State Council of the People’s Republic of China, 2021, 17: 174-178.
6.	国务院办公厅发布关于推动公立医院高质量发展的意见, 提出强化信息化支撑作用. 医学信息学杂志, 2021, 42 (6): 95.The General Office of the State Council issued opinions on promoting the high-quality development of public hospitals, proposing to strengthen the role of information technology support. J Med Inform, 2021, 42 (6): 95.
7.	张妍. AI+医疗, 近450个应用落地. 深圳商报, 2025-03-11(A03).Zhang Y. AI+healthcare: Nearly 450 applications implemented. Shenzhen Commercial Daily, 2025-03-11 (A03).
8.	田雪晴, 李泉江, 游茂, 等. 我国医疗机构大语言模型建设现状调查与分析. 中国卫生信息管理杂志, 2025, 22(1): 38-44.Tian XQ, Li QJ, You M, et al. Survey and analysis of the current status of large language model development in medical institutions in China. Chin J Health Inform Manag, 2025, 22(1): 38-44.
9.	Bodenreider O. The unified medical language system (UMLS): Integrating biomedical terminology. Nucl Acids Res, 2004, 32(suppl_1): D267-D270.
10.	Donnelly K. SNOMED-CT: The advanced terminology and coding system for eHealth. Studies in health technology and informatics, 2006, 121: 279.
11.	费菲, 曲莉莉, 赵海. 改吗?!46%的医师上班近4成时间写病历本刊《病历书写基本规范》20月调查结果新鲜出炉. 中国医药科学, 2017, 7(21): 1-8.Fei F, Qu LL, Zhao H. Should it be changed?! 46% of doctors spend nearly 40% of their working hours writing medical records. The latest survey results from our publication “Basic Standards for Medical Record Writing” are freshly released after 20 months. China Med Pharm, 2017, 7(21): 1-8.
12.	微软公司. Microsoft Dragon Copilot : Lle premier assistant vocal IA unifié pour le secteur de la santé. (2025-03-03)[2025-04-08].

1. 张霄. 三部门联合印发《卫生健康行业人工智能应用场景参考指引》. 中医药管理杂志, 2024, 32(22): 35.Zhang X. Three departments jointly issued "the reference duide for AI application scenarios in the healthcare industry". J Trad Chin Med Manag, 2024, 32(22): 35.
2. 国家发展改革委. 国家发展改革委商务部关于《鼓励外商投资产业目录(2020年版)(征求意见稿)》公开征求意见的通知. 中国对外经济贸易文告, 2020, 54: 10-27.National Development and Reform Commission. Notice on Public Solicitation of Opinions on the “Catalog of Industries Encouraging Foreign Investment (2020 Edition) (Draft for Comments)” by the National Development and Reform Commission and the Ministry of Commerce. China Foreign Trade and Economic Cooperation Gazette, 2020, 54: 10-27.
3. 中共中央国务院印发《数字中国建设整体布局规划》. 人民日报, 2023-02-28.001). The Central Committee of the Communist Party of China and the State Council issued the "Overall Layout Plan for Digital China Construction". People's Daily, 2023-02-28 (001).
4. 王春晖. 《数字中国建设整体布局规划》的深入解读. 通信世界, 2023, 5: 4-5.Wang CH. Interpretation of the “overall layout plan for digital China construction”. Commun World, 2023, 5: 4-5.
5. 国务院办公厅关于推动公立医院高质量发展的意见. 中华人民共和国国务院公报, 2021, 17: 174-178.Opinions of the General Office of the State Council on promoting the high-quality development of public hospitals. Gazette of the State Council of the People’s Republic of China, 2021, 17: 174-178.
6. 国务院办公厅发布关于推动公立医院高质量发展的意见, 提出强化信息化支撑作用. 医学信息学杂志, 2021, 42 (6): 95.The General Office of the State Council issued opinions on promoting the high-quality development of public hospitals, proposing to strengthen the role of information technology support. J Med Inform, 2021, 42 (6): 95.
7. 张妍. AI+医疗, 近450个应用落地. 深圳商报, 2025-03-11(A03).Zhang Y. AI+healthcare: Nearly 450 applications implemented. Shenzhen Commercial Daily, 2025-03-11 (A03).
8. 田雪晴, 李泉江, 游茂, 等. 我国医疗机构大语言模型建设现状调查与分析. 中国卫生信息管理杂志, 2025, 22(1): 38-44.Tian XQ, Li QJ, You M, et al. Survey and analysis of the current status of large language model development in medical institutions in China. Chin J Health Inform Manag, 2025, 22(1): 38-44.
9. Bodenreider O. The unified medical language system (UMLS): Integrating biomedical terminology. Nucl Acids Res, 2004, 32(suppl_1): D267-D270.
10. Donnelly K. SNOMED-CT: The advanced terminology and coding system for eHealth. Studies in health technology and informatics, 2006, 121: 279.
11. 费菲, 曲莉莉, 赵海. 改吗?!46%的医师上班近4成时间写病历本刊《病历书写基本规范》20月调查结果新鲜出炉. 中国医药科学, 2017, 7(21): 1-8.Fei F, Qu LL, Zhao H. Should it be changed?! 46% of doctors spend nearly 40% of their working hours writing medical records. The latest survey results from our publication “Basic Standards for Medical Record Writing” are freshly released after 20 months. China Med Pharm, 2017, 7(21): 1-8.
12. 微软公司. Microsoft Dragon Copilot : Lle premier assistant vocal IA unifié pour le secteur de la santé. (2025-03-03)[2025-04-08].

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Latest ArticlesConstruction and application of the “Huaxi Hongyi” large medical model

Abstract Full text Figures/Tables Video References Cited by

Format

Content