OpenAI announced that physicians rated 99.1% of ChatGPT responses safe across 4,363 evaluations covering 27 clinical use cases. The announcement introduces an Epic EHR integration bringing authorized patient context into ChatGPT for Healthcare, plus a Healthcare Public Data plugin connecting nine official sources including CMS Coverage, PubMed, and DailyMed. In separate testing, over 93% of responses across five connected data sources were rated "good" or better accuracy.
No score is assigned. Sources and their independence are shown in the citation chain below.