Towards conversational artificial intelligence for disease management
6 affiliations
- 1Google DeepMind, Mountain View, CA, USA. [email protected]
- 2Google Research, Mountain View, CA, USA. [email protected]
- 3Google Research, Mountain View, CA, USA
- 4Google DeepMind, Mountain View, CA, USA
- 5Google Research, Mountain View, CA, USA. [email protected]
- 6Google Research, Mountain View, CA, USA. [email protected]
Abstract
Although large language models have shown promise in diagnostic dialogue 1 , their capabilities for effective management reasoning, including disease progression, therapeutic response and safe medication prescription, have remained underexplored. We have advanced the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE) 1–3 using a new large-language-model-based agentic system optimized for multivisit clinical management and dialogue. To ground the reasoning of AMIE in authoritative clinical knowledge, we leveraged the long-context capabilities of Gemini 4 , 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 study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multivisit case scenarios designed to reflect the guidance of the UK National Institute for Health and Care Excellence and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning, as assessed by specialists, and scored better both with respect to preciseness of treatment and investigation, and in terms of its alignment with and grounding in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark that was derived from two national drug formularies (from the USA and UK) and validated by board-certified pharmacists. Although AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher-difficulty questions. Although further research will be needed before real-world translation of AMIE, its strong performance across evaluations marks a significant step towards use of conversational artificial intelligence as a tool in disease management.
Related
- How artificial intelligence could improve the diagnosis and management of chronic obstructive pulmonary disease: a perspective from GOLD
- Conversational diagnostic artificial intelligence in ambulatory primary care: a prospective feasibility study
- Conversational artificial intelligence for pre-procedural patient preparation: implementation, validation and patient satisfaction
- Subversion of clinical judgment by conversational artificial intelligence
- Harnessing conversational generative artificial intelligence and natural language processing to address the colorectal cancer screening adherence gap: the Azores endeavour
BibTeX
@article{lievin2026towards,
title = {{Towards conversational artificial intelligence for disease management}},
author = {Valentin Liévin and Anil K. Palepu and Wei‐Hung Weng and Khaled Kamal Saab and David Stutz and Yong Cheng and Kavita Kulkarni and S. Sara Mahdavi and Joelle K. Barral and Dale R. Webster and Katherine Chou and Avinatan Hassidim and Yossi Matias and James Manyika and Ryutaro Tanno and Vivek Natarajan and Adam M. Rodman and Tao Tu and Alan Karthikesalingam and Mike Schaekermann},
journal = {Nature},
year = {2026},
month = jun,
doi = {10.1038/s41586-026-10764-5},
url = {https://doi.org/10.1038/s41586-026-10764-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - Towards conversational artificial intelligence for disease management
AU - Valentin Liévin
AU - Anil K. Palepu
AU - Wei‐Hung Weng
AU - Khaled Kamal Saab
AU - David Stutz
AU - Yong Cheng
AU - Kavita Kulkarni
AU - S. Sara Mahdavi
AU - Joelle K. Barral
AU - Dale R. Webster
AU - Katherine Chou
AU - Avinatan Hassidim
AU - Yossi Matias
AU - James Manyika
AU - Ryutaro Tanno
AU - Vivek Natarajan
AU - Adam M. Rodman
AU - Tao Tu
AU - Alan Karthikesalingam
AU - Mike Schaekermann
PY - 2026
DA - 2026/06/17
JO - Nature
DO - 10.1038/s41586-026-10764-5
UR - https://doi.org/10.1038/s41586-026-10764-5
AB - Although large language models have shown promise in diagnostic dialogue 1 , their capabilities for effective management reasoning, including disease progression, therapeutic response and safe medication prescription, have remained underexplored. We have advanced the previously demonstrated diagnostic capabilities of the Articulate Medical Intelligence Explorer (AMIE) 1–3 using a new large-language-model-based agentic system optimized for multivisit clinical management and dialogue. To ground the reasoning of AMIE in authoritative clinical knowledge, we leveraged the long-context capabilities of Gemini 4 , 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 study, AMIE was compared to 21 primary care physicians (PCPs) across 100 multivisit case scenarios designed to reflect the guidance of the UK National Institute for Health and Care Excellence and BMJ Best Practice guidelines. AMIE was non-inferior to PCPs in management reasoning, as assessed by specialists, and scored better both with respect to preciseness of treatment and investigation, and in terms of its alignment with and grounding in clinical guidelines. To benchmark medication reasoning, we developed RxQA, a multiple-choice question benchmark that was derived from two national drug formularies (from the USA and UK) and validated by board-certified pharmacists. Although AMIE and PCPs both benefited from the ability to access external drug information, AMIE outperformed PCPs on higher-difficulty questions. Although further research will be needed before real-world translation of AMIE, its strong performance across evaluations marks a significant step towards use of conversational artificial intelligence as a tool in disease management.
SN - 0028-0836
SN - 1476-4687
ER -