Journal Article

Towards conversational diagnostic artificial intelligence

Natarajan, Vivek, Tanno, Ryutaro, Freyberg, Jan, Barral, Joelle, Gottweis, Juraj, Wang, Amy, Cheng, Yong, Singhal, Karan, Corrado, Greg S., Amin, Mohamed, Mahdavi, S. Sara, Hou, Le, Vedadi, Elahe, Chou, Katherine, Kulkarni, Kavita, Tomasev, Nenad, Karthikesalingam, Alan, Tu, Tao, Palepu, Anil, Schaekermann, Mike, Li, Brenna, Saab, Khaled, Semturs, Christopher, Matias, Yossi, Webson, Albert, Azizi, Shekoofeh

2025

Overview

At the heart of medicine lies physician–patient dialogue, where skillful history-taking enables effective diagnosis, management and enduring trust 1 , 2 . Artificial intelligence (AI) systems capable of diagnostic dialogue could increase accessibility and quality of care. However, approximating clinicians’ expertise is an outstanding challenge. Here we introduce AMIE (Articulate Medical Intelligence Explorer), a large language model (LLM)-based AI system optimized for diagnostic dialogue. AMIE uses a self-play-based 3 simulated environment with automated feedback for scaling learning across disease conditions, specialties and contexts. We designed a framework for evaluating clinically meaningful axes of performance, including history-taking, diagnostic accuracy, management, communication skills and empathy. We compared AMIE’s performance to that of primary care physicians in a randomized, double-blind crossover study of text-based consultations with validated patient-actors similar to objective structured clinical examination 4 , 5 . The study included 159 case scenarios from providers in Canada, the United Kingdom and India, 20 primary care physicians compared to AMIE, and evaluations by specialist physicians and patient-actors. AMIE demonstrated greater diagnostic accuracy and superior performance on 30 out of 32 axes according to the specialist physicians and 25 out of 26 axes according to the patient-actors. Our research has several limitations and should be interpreted with caution. Clinicians used synchronous text chat, which permits large-scale LLM–patient interactions, but this is unfamiliar in clinical practice. While further research is required before AMIE could be translated to real-world settings, the results represent a milestone towards conversational diagnostic AI. The conversational diagnostic artificial intelligence system AMIE (Articulate Medical Intelligence Explorer) has potential as a real-world tool for clinical history-taking and diagnostic dialogue, based on its performance in simulated consultations.

• Publisher: Nature Publishing Group UK,Nature Publishing Group
• Subject: 692/308 / 692/700/139 / Accuracy / Artificial Intelligence / Automation / Canada / Clinical trials / Communication / Communication skills / Diagnosis / Double-Blind Method / Empathy / Female / Health care / Humanities and Social Sciences / Humans / India / Internal medicine / Language / Large language models / Male / Medical History Taking / Medicine / multidisciplinary / Patients / Physician-Patient Relations / Physicians / Physicians, Primary Care - psychology / Primary care / Science / Science (multidisciplinary) / United Kingdom / Verbal communication