03/15/26

A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic.

Brodeur, Peter; Koshy, Jacob M; Palepu, Anil; Saab, Khaled; Homiar, Ava; Ruparel, Roma; Wu, Charles; Tanno, Ryutaro; Xu, Joseph; Wang, Amy; Stutz, David; Ferrera, Hannah M; Barrett, David; Crowley, Lindsey; Lee, Jihyeon; Rittner, Spencer E; Wulczyn, Ellery; Zhang, Selena K; Vedadi, Elahe; Kohn, Christine G; Kulkarni, Kavita; Kadiyala, Vinay; Mahdavi, Sara; Du, Wendy; Williams, Jessica; Feinbloom, David; Wong, Renee; Tu, Tao; Sirkovic, Petar; Orlandi, Alessio; Semturs, Christopher; Liu, Yun; Gottweis, Juraj; Webster, Dale R; Barral, Joëlle; Chou, Katherine; Kohli, Pushmeet; Hassidim, Avinatan; Matias, Yossi; Manyika, James; Fields, Rob; Li, Jonathan X; Cohen, Marc L; Natarajan, Vivek; Schaekermann, Mike; Karthikesalingam, Alan; Rodman, Adam. ArXiv.

Summary

LLM-based AI systems may improve patient diagnostic conversations, but there is limited real-world evidence. This pre-print feasibility study tests Google’s Articulate Medical Intelligence Explorer (AMIE) for history taking and diagnosis presentation. The results suggest AMIE can safely collect histories and generate diagnostic suggestions, but the authors also acknowledge limited generalizability due to the study taking place at a single center and the 100 participant sample size.

Brodeur P, Koshy JM, Palepu A, et al. A prospective clinical feasibility study of a conversational diagnostic AI in an ambulatory primary care clinic. arXiv. Epub 2026 Mar 15.