Clinical questions and evidence search
AI search tools and chatbots that answer clinicians' medical questions in plain language, from the medical literature, an expert-written reference or a general-purpose model.
Category overviewHide category overview
These tools answer clinicians' medical questions in conversational form. In a 2026 American Medical Association survey of nearly 1,700 physicians, 81% reported using AI professionally, more than double the 2023 rate. FDA's guidance on clinical decision support software describes the types of decision-support functions excluded from the definition of a device; no FDA clearance was found for any of the tools reviewed here.
A systematic review of 519 studies of large language models in health care found 5% evaluated them on real patient care data. A 2026 review of 4,609 such studies in clinical medicine found 1,048 that used real-world patient data, 19 of them prospective randomized trials. In NOHARM, a preprint that tested 20 large language models and four retrieval-based clinical tools on a 1,100-task benchmark of primary care-to-specialist consultation cases, applying the recommendations directly carried potential for severe harm in up to 24.6% of cases; omissions accounted for more than 80% of severe errors. Open questions include whether the answers change clinicians' decisions and patient outcomes in routine care.
AMBOSS AI
AI question-answering features of AMBOSS, the clinician-curated medical knowledge platform and question bank used by medical students and physicians.
Read the full review with Pro
The grade is free. The evidence behind it, the prices and every source are for members.
Founding Pro: $149 a year, locked while you stay. Until Dec. 31. Regular price $249 a year.
Already a member? Sign in
ChatGPT
OpenAI's general-purpose chatbot, used by clinicians for clinical questions, with versions for individual clinicians and health systems.
Caution. In a simulation study of 300 physician-validated vignettes, each containing one fabricated detail, GPT-4o, the top performer among six models, repeated or elaborated on the false detail in 53% of cases, and in 23% with a mitigation prompt. In a randomized vignette trial of 44 physicians in Pakistan, reported in a preprint, those shown deliberately flawed ChatGPT-4o recommendations had mean diagnostic accuracy of 73.3%, versus 84.9% with unmodified ones.
Claude
Anthropic's general-purpose AI chatbot and the Claude family of large language models behind it, tested on clinical questions.
Caution. In an independent physician red-teaming study of 222 primary care questions posed as patients would ask them, physicians rated 21.6% of Claude 3.5 Sonnet's answers problematic and 5.0% unsafe. That was the lowest unsafe rate of the four chatbots tested; GPT-4o's was 13.5%.
ClinicalKey AI
Elsevier's clinical reference tool that answers clinicians' questions with generated summaries citing a curated set of medical content.
DeepSeek
DeepSeek's general-purpose AI chatbot and its family of open-source large language models, deployed in Chinese hospitals and tested on clinical questions and cases.
Doximity GPT
Writing and question-answering chatbot for clinicians on the Doximity professional network, described in 2025 as using OpenAI's GPT-4.
Dyna AI
EBSCO's generative AI chatbot that answers clinicians' questions, from the company that publishes the DynaMed clinical reference.
Glass Health
AI clinical decision support tool that generates differential diagnoses and answers clinical questions from a clinician's case description.
Google Gemini
Google's general-purpose AI chatbot and the Gemini family of large language models behind it, tested on clinical questions and cases.
Caution. In an independent physician red-teaming study of 222 primary care questions posed as patients would ask them, physicians rated 27.5% of Gemini 1.5 Flash's answers problematic. In a BMJ study, PaLM 2 and Gemini Pro, used through Bard, consistently generated health disinformation blogs on request.
OpenEvidence
AI search tool that answers clinicians' questions with a summary of the medical literature and citations.
UpToDate Expert AI
Generative AI chat feature in UpToDate that answers clinical questions from UpToDate's expert-authored, peer-reviewed content.
Reviews of the published evidence, not medical advice or an endorsement of any product.