Artificial Intelligence Deployment of Conversational Support (AI-DOCS): A patient acceptability study

This study evaluated an artificial intelligence (AI) system based on a large language model (LLM) in conducting complex patient assessments, comparing its acceptability to that of human basic physician trainees (BPTs) during a divisional clinical examination (DCE). Compared with BPTs, Artificial Intelligence Deployment of Conversational Support (AI-DOCS) scored similarly empathy, politeness, and comprehensiveness to human trainees. AI-DOCS also elicited important clinical information that was not divulged to human examiners. Further research is needed to explore the integration of AI-DOCS into clinical workflows.