Dynamic Closed-Loop Medical Record Quality Management Using an AI-Driven Multilevel Quality Control System:...

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Quality Management Systems

Background:

• Traditional manual quality control (QC) for medical records suffers from limited coverage, inefficiency, and inconsistent standards.
• These limitations hinder hospitals in meeting modern quality and safety requirements for clinical documentation.

Purpose of the Study:

• To develop an AI-driven platform for medical record quality control.
• To establish a multilevel QC system using this platform to enhance electronic medical records (EMRs).

Main Methods:

• Established a QC rule database aligned with medical record writing standards.
• Developed an AI-driven QC engine integrating deep learning and natural language processing.
• Designed and implemented a 4-level QC and management process in a tertiary hospital.

Main Results:

• Achieved 100% automated initial screening coverage for EMRs using AI.
• Implemented a human-machine collaborative QC model with efficient closed-loop operations.
• Significantly improved EMR completeness, timeliness, consistency, and accuracy, with notable increases in grade A and excellent rates (P<.001).

Conclusions:

• An AI-based 4-level QC management model effectively overcomes traditional QC limitations.
• The model facilitates comprehensive, dynamic, and closed-loop EMR management, enhancing overall medical record quality.
• This AI-driven approach offers a valuable reference for hospital QC model reform.