Construction and application of an auxiliary decision-making system for diagnosis omissions based on artificial intelligence technology
10.3760/cma.j.cn111325-20240910-00787
- VernacularTitle:基于人工智能技术的疾病诊断漏写辅助决策系统构建及应用
- Author:
Naipeng LIU
1
;
Mengxiang YOU
;
Zhenkun LI
;
Yang XIANG
;
Fei ZHAI
;
Xiaohong CHU
Author Information
1. 中国科学技术大学附属第一医院（安徽省立医院）病案统计室，合肥 230001
- Publication Type:Journal Article
- Keywords:
Medical record homepage;
Medical insurance payment;
Diagnosis-related groups;
Artificial intelligence;
Diagnosis omission;
Auxiliary decision-making system
- From:
Chinese Journal of Hospital Administration
2025;41(8):619-623
- CountryChina
- Language:Chinese
-
Abstract:
Medical record homepage is a core basis for healthcare quality management, medical insurance payment, and public hospital performance evaluation.The completeness and accuracy of its data directly affect the medical quality and economic benefits of hospitals. Since July 2022, a tertiary hospital had built an auxiliary decision-making system for diagnosis omissions based on artificial intelligence technology, which was officially launched in January 2023. The system aimed to improve the quality of data on the first page of medical records and ensure reasonable payment by medical insurance. This system was built on the hospital′s electronic medical records, and integrated natural language processing, medical knowledge graphs and deep learning technologies to create three engines: diagnosis omission recognition, ICD coding and DRG grouping. The diagnosis omission recognition engine identified both explicit and implicit omitted diagnoses by using a context semantic analysis model and a contrastive learning framework for dual judgment. It also interacted with the ICD coding and DRG grouping engines to enhance the accuracy of DRG grouping. Since its launched, the system has achieved remarkable results. A comparative analysis revealed that the rate of missing diagnoses on hospital medical record homepages has decreased from 31.31% during January to September 2022 to 12.34% during the same period in 2023, and the quality control time for a single medical record had been reduced from 20 minutes to 5 minutes. Additionally, a simulation calculation showed that the system-assisted DRG grouping can increase the hospital′s medical insurance surplus. The system could provide reference and guidance for public hospitals in China to improve the quality of the homepage of medical records and better adapt to medical insurance payment reform.
