Quality safety and disparity of an AI chatbot in managing chronic diseases: simulated patient experiments
8.3
来源：
Nature
关键字：
digital pathology
发布时间：
2025-09-25 23:56
摘要：
ERNIE Bot, an AI chatbot developed by Baidu, was evaluated for its effectiveness in managing chronic diseases through simulated patient experiments. The study found that while ERNIE Bot achieved a diagnostic accuracy of 77.3% and correct drug prescriptions of 94.3%, it also exhibited high rates of unnecessary medical tests (91.9%) and inappropriate medications (57.8%). The research highlights significant disparities in healthcare access and quality, particularly influenced by patient age and economic status, underscoring the need for careful integration of AI in healthcare systems.
原文：
查看原文
价值分投票
评分标准
新闻价值分采用0-10分制，综合考虑新闻的真实性、重要性、时效性、影响力等多个维度。
评分越高，表示该新闻的价值越大，越值得关注。
价值维度分析
domain_focus
1.0分+1.0分
business_impact
0.8分+0.8分
scientific_rigor
1.5分+1.5分
timeliness_innovation
1.5分+1.5分
investment_perspective
2.5分+2.5分
market_value_relevance
1.0分+1.0分
team_institution_background
0.5分+0.5分
technical_barrier_competition
0.7分+0.7分
关键证据
ERNIE Bot reached a diagnostic accuracy of 77.3% and correct drug prescriptions of 94.3%.
The study evaluates the quality, safety, and disparity of medical consultations provided by ERNIE Bot.
Disparities were observed based on patient age and household economic status.
真实性检查
否
AI评分总结
ERNIE Bot, an AI chatbot developed by Baidu, was evaluated for its effectiveness in managing chronic diseases through simulated patient experiments. The study found that while ERNIE Bot achieved a diagnostic accuracy of 77.3% and correct drug prescriptions of 94.3%, it also exhibited high rates of unnecessary medical tests (91.9%) and inappropriate medications (57.8%). The research highlights significant disparities in healthcare access and quality, particularly influenced by patient age and economic status, underscoring the need for careful integration of AI in healthcare systems.