Large language models for generating disability reports and assigning impairment percentages for health commissions

This study explores the use of artificial intelligence tools to assist health commissions in calculating disability percentages, aiming to alleviate the administrative burden on physicians. The performance of two advanced AI systems, ChatGPT-4 and Data Analyst, was evaluated based on their ability to generate accurate disability reports and percentage calculations for nine realistic patient scenarios. These outputs were assessed using a 5-point Likert scale, focusing on alignment with expert evaluations and established disability guidelines, completeness, and accuracy (absence of false information). The findings underscore the potential of integrating AI tools into health commission workflows to streamline processes and enhance efficiency.本研究探索了人工智能工具辅助卫生委员会开展残疾百分比计算的应用路径，旨在减轻医师群体的行政工作负担。本研究针对两款先进人工智能系统——ChatGPT-4与数据分析员（Data Analyst）的性能进行评估，评估依据为其针对九种真实患者场景生成准确残疾评定报告及残疾百分比计算结果的能力。本次评估采用5级李克特量表（5-point Likert scale），重点考察系统输出与专家评定结果及既定残疾评定指南的契合度、内容完整性以及信息准确性（无虚假信息）。研究结果凸显了将人工智能工具融入卫生委员会工作流程，以优化作业流程、提升工作效率的应用潜力。