JMIR Publications

ABSTRACT

Background:

As the core carrier of the clinical diagnosis and treatment process, the quality of medical records is directly related to medical safety and efficiency. However, traditional manual quality control (QC) has problems such as limited coverage, low efficiency, and inconsistent standards, which are difficult to meet the high standards of modern hospitals.

Objective:

The purpose of this study is to develop a medical record QC platform based on artificial intelligence (AI) technology, and to build a multi-level QC system relying on the platform to comprehensively improve the form and content of electronic medical records (EMR).

Methods:

This study established a QC rule database based on relevant medical record writing standards, combined deep learning and natural language processing technologies to build an AI-driven QC engine, designed a four-level QC and management process, and implemented it in a comprehensive tertiary hospital in China.

Results:

After the application of the AI-based four-level QC system, a new model of medical record quality management with human-machine combination, interaction between QC units and clinical departments, efficient closed-loop, and equal emphasis on form and connotation was formed. The QC coverage rate of EMR in the hospital reached 100%, the completeness, timeliness, consistency and accuracy were effectively improved. Meanwhile, various indicators such as the grade A rate and excellent rate were significantly increased.

Conclusions:

This study confirms that an AI-assisted four-level QC system can overcome the limitations of traditional manual QC methods, enabling comprehensive, dynamic, and closed-loop management of EMR throughout their entire lifecycle, thereby significantly improving the overall quality of medical records, which can provide a reference for other hospitals to promote QC system reforms.