Towards Conversational AI for Disease Management

Article

Published: 17 June 2026

Valentin Liévin

ORCID: orcid.org/0000-0002-6096-95641 na2,

Anil Palepu

ORCID: orcid.org/0000-0002-4720-87872 na2,

Wei-Hung Weng

ORCID: orcid.org/0000-0003-2232-03902,

Khaled Saab

ORCID: orcid.org/0000-0003-1427-04691,

David Stutz1,

Yong Cheng1,

Kavita Kulkarni2,

S. Sara Mahdavi1,

Joëlle Barral1,

Dale R. Webster

ORCID: orcid.org/0000-0002-3023-88242,

Katherine Chou2,

Avinatan Hassidim2,

Yossi Matias

ORCID: orcid.org/0000-0003-3960-60022,

James Manyika2,

Ryutaro Tanno

ORCID: orcid.org/0000-0002-8107-67301,

Vivek Natarajan

ORCID: orcid.org/0000-0001-7849-20742,

Adam Rodman2,

Tao Tu

ORCID: orcid.org/0000-0001-9191-79381,

Alan Karthikesalingam

ORCID: orcid.org/0009-0000-4958-59762 na1 &

…

Mike Schaekermann

ORCID: orcid.org/0000-0002-1735-96802 na1

Nature

(2026) Cite this article

We are providing an unedited version of this manuscript to give early access to its

findings. Before final publication, the manuscript will undergo further editing. Please note

there may be errors present which affect the content, and all legal disclaimers apply.

Abstract

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.

Similar content being viewed by others

Author information

Author notes

These authors jointly supervised this work: Alan Karthikesalingam, Mike Schaekermann

These authors contributed equally: Valentin Liévin, Anil Palepu

Authors and Affiliations

Google DeepMind, Mountain View, California, USA

Valentin Liévin, Khaled Saab, David Stutz, Yong Cheng, S. Sara Mahdavi, Joëlle Barral, Ryutaro Tanno & Tao Tu

Google Research, Mountain View, California, USA

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

Authors

Valentin Liévin

Anil Palepu

Wei-Hung Weng

Khaled Saab

David Stutz

Yong Cheng

Kavita Kulkarni

S. Sara Mahdavi

Joëlle Barral

Dale R. Webster

Katherine Chou

Avinatan Hassidim

Yossi Matias

James Manyika

Ryutaro Tanno

Vivek Natarajan

Adam Rodman

Tao Tu

Alan Karthikesalingam

Mike Schaekermann

Corresponding authors

Correspondence to

Valentin Liévin, Anil Palepu, Alan Karthikesalingam or Mike Schaekermann.

Supplementary information

Supplementary Information (download PDF )

Supplementary discussion, methods and results (Sections 1-16). Contains related work, details on the system design for the Mx agent and Dialogue agent, details on the OSCE evaluation study (inter-rater reliability analysis, clinician metadata, scenario metadata, ablation analysis), and methods details and further results for the RxQA medication reasoning benchmark.

Reporting Summary (download PDF )

Supplementary Data 1 (download PDF )

Detailed view of two sample scenarios with AMIE and PCP output and evaluation gradings. Full details for two sample scenarios used in the OSCE evaluation study, including scenario information, AMIE-patient-actor conversations, PCP-patient-actor conversations, specialist physician gradings and patient actor gradings for all three visits per scenario.

Supplementary Data 2 (download PDF )

Details for all 120 OSCE scenarios with AMIE output (PDF). Scenario details and AMIE output for all 120 scenarios used either in the OSCE evaluation study (100) or for validation purposes (20), in human-readable PDF format.

Supplementary Data 3 (download CSV )

Details for all 120 OSCE scenarios with AMIE output (CSV). Scenario details and AMIE output for all 120 scenarios used either in the OSCE evaluation study (100) or for validation purposes (20), in machine-readable CSV format.

Peer Review File (download PDF )

About this article

Cite this article

Liévin, V., Palepu, A., Weng, WH. et al. Towards Conversational AI for Disease Management.

Nature (2026). https://doi.org/10.1038/s41586-026-10764-5

Download citation

Received: 17 March 2025

Accepted: 04 June 2026

Published: 17 June 2026

DOI: https://doi.org/10.1038/s41586-026-10764-5

You have full access to this article via your institution.