Towards Conversational AI for Disease Management | Nature

Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain<br>the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in<br>Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles<br>and JavaScript.

Advertisement

Towards Conversational AI for Disease Management

Download PDF

Subjects

Diseases<br>Health care

Abstract<br>While large language models (LLMs) have shown promise in diagnostic dialogue1, their capabilities for effective management reasoning—including disease progression, therapeutic response, and safe medication prescription—remain under-explored. We advance the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE)1−3 through a new LLM-based agentic system optimized for multi-visit clinical management and dialogue. To ground its reasoning in authoritative clinical knowledge, AMIE leverages Gemini’s long-context capabilities4, combining in-context retrieval with structured reasoning to align its output with up-to-date clinical practice guidelines and drug formularies. In a randomized, blinded virtual Objective Structured Clinical Examination (OSCE) study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multi-visit case scenarios designed to reflect UK NICE Guidance and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning as assessed by specialists and scored better in both preciseness of treatments and investigations, and in its alignment with and grounding in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark derived from two national drug formularies (US, UK) and validated by board-certified pharmacists. Though AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher difficulty questions. While further research would be needed before real-world translation, AMIE’s strong performance across evaluations marks a significant step towards conversational AI as a tool in disease management.

You have full access to this article via your institution.

Download PDF

Similar content being viewed by others

Towards conversational diagnostic artificial intelligence

Article<br>Open access<br>09 April 2025

Advancing conversational diagnostic AI with multimodal reasoning

Article<br>Open access<br>14 May 2026

Towards accurate differential diagnosis with large language models

Article<br>Open access<br>09 April 2025

Author information<br>Author notesThese authors jointly supervised this work: Alan Karthikesalingam, Mike Schaekermann

These authors contributed equally: Valentin Liévin, Anil Palepu

Authors and Affiliations<br>Google DeepMind, Mountain View, California, USA<br>Valentin Liévin, Khaled Saab, David Stutz, Yong Cheng, S. Sara Mahdavi, Joëlle Barral, Ryutaro Tanno & Tao Tu

Google Research, Mountain View, California, USA<br>Anil Palepu, Wei-Hung Weng, Kavita Kulkarni, Dale R. Webster, Katherine Chou, Avinatan Hassidim, Yossi Matias, James Manyika, Vivek Natarajan, Adam Rodman, Alan Karthikesalingam & Mike Schaekermann

AuthorsValentin LiévinView author publications<br>Search author on:PubMed Google Scholar

Anil PalepuView author publications<br>Search author on:PubMed Google Scholar

Wei-Hung WengView author publications<br>Search author on:PubMed Google Scholar

Khaled SaabView author publications<br>Search author on:PubMed Google Scholar

David StutzView author publications<br>Search author on:PubMed Google Scholar

Yong ChengView author publications<br>Search author on:PubMed Google Scholar

Kavita KulkarniView author publications<br>Search author on:PubMed Google Scholar

S. Sara MahdaviView author publications<br>Search author on:PubMed Google Scholar

Joëlle BarralView author publications<br>Search author on:PubMed Google Scholar

Dale R. WebsterView author publications<br>Search author on:PubMed Google Scholar

Katherine ChouView author publications<br>Search author on:PubMed Google Scholar

Avinatan HassidimView author publications<br>Search author on:PubMed Google Scholar

Yossi MatiasView author publications<br>Search author on:PubMed Google Scholar

James ManyikaView author publications<br>Search author on:PubMed Google Scholar

Ryutaro TannoView author publications<br>Search author on:PubMed Google Scholar

Vivek NatarajanView author publications<br>Search author on:PubMed Google Scholar

Adam RodmanView author publications<br>Search author on:PubMed Google Scholar

Tao TuView author publications<br>Search author on:PubMed Google Scholar

Alan KarthikesalingamView author publications<br>Search author on:PubMed Google Scholar

Mike SchaekermannView author publications<br>Search author on:PubMed Google Scholar

Corresponding authors<br>Correspondence to<br>Valentin Liévin, Anil Palepu, Alan Karthikesalingam or Mike Schaekermann.

Supplementary...