ArticleNPJ digital medicine2026
Large language models provide unsafe answers to patient-posed medical questions.
Article in NPJ digital medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 23 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
23 citing papers in PubMed.
- Development and Nationwide Multicentre Evaluation of Guideline-Grounded Large Language Model Chatbots to Support Patient Self-Management and Education in Rheumatology.Journal of medical systems · 2026Article
- Validating LLM judges for automated oversight of patient communication.medRxiv : the preprint server for health sciences · 2026Article
- Article
- The Reliability of Human Evaluation of Large Language Models in Health Care Settings: Scoping Review.Journal of medical Internet research · 2026Article
- Comparative Evaluation of ChatGPT-5.2, Claude Sonnet 4.5, and DeepSeek-V3.2 for Rosacea-Related Information: Accuracy, Reliability, Readability, and Reference Hallucinations.Diagnostics (Basel, Switzerland) · 2026Article
- An Analysis of the Nutritional Value of Diets Generated by Large Language Models Under Average User Conditions-3(LM)Diet Study.Nutrients · 2026Article
- Evaluating the safety of large language models in healthcare and dentistry: adversarial testing approaches.BDJ open · 2026Review
- Structured Large Language Model Workflows for Motivational Interviewing in Health Behavior Change: Proof-of-Concept Study.JMIR formative research · 2026Article
- Clinical Safety and Reliability of Large Language Models in Answering Hemorrhoid-Related Patient Questions: A Comparative Study of ChatGPT, Gemini, and DeepSeek.Healthcare (Basel, Switzerland) · 2026Article
- The Third Presence in the Clinic Room: How Artificial Intelligence Is Reshaping the Clinical Encounter.Mayo Clinic proceedings. Digital health · 2026Review
- Integrating Generative AI Into Patient-Centered Clinical Decision Support: Viewpoint on Research and Practice Considerations.Journal of medical Internet research · 2026Article
- Performance of ChatGPT in dental implant treatment planning: evaluation using the modified DISCERN, Global Quality Score, and accuracy-safety score.BMC oral health · 2026Article
- Review
- Evaluating search-enabled large language model interfaces for mpox public health consultation: a guideline-based comparative study.Frontiers in public health · 2026Article
- Compliance of large language model generated meal plans with polish dietary recommendations: a real-world evaluation under average user conditions-3(LM)Diet study.Frontiers in public health · 2026Article
- Evaluation of generative AI-driven chatbots as sources of consumer health information on hand, foot, and mouth disease: a cross-sectional comparative study of safety, accuracy, information quality, readability, and empathy.Frontiers in public health · 2026Article
- Evaluating sports nutrition advice provided by general-purpose large language models for recreational female marathon runners: a multidimensional descriptive audit.Frontiers in nutrition · 2026Article
- Assessing the information quality of AI-generated patient educational materials for diabetes: a scoping review.Frontiers in public health · 2026Article
- ChatGPT-generated rehabilitation programs in sports physiotherapy: an expert evaluation and a mixed-methods study of clinical applicability.Frontiers in medicine · 2026Article
- Generative AI use before medical visits: disclosure-item responses, trust, and care-seeking behaviors in a cross-sectional social-media survey in Poland.Frontiers in digital health · 2026Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
17 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Millions of patients are regularly using large language model (LLM) chatbots for medical advice, raising patient safety concerns. This physician-led red-teaming study compares the safety of four publicly available chatbots-Claude by Anthropic, Gemini by Google, GPT-4o by OpenAI, and Llama-3.0/3.1-70B by Meta-on a new dataset, HealthAdvice, using an evaluation framework that enables quantitative and qualitative analysis. In total, 888 chatbot responses are evaluated for 222 patient-posed advice-seeking medical questions on primary care topics spanning internal medicine, women's health, and pediatrics. We find statistically significant differences between chatbots. The rate of problematic responses varies from 21.6% (Claude) to 43.2% (Llama), with unsafe responses varying from 5% (Claude) to 13% (GPT-4o, Llama). Qualitative results reveal chatbot responses with the potential to lead to serious patient harm. This study suggests that millions of patients could be receiving unsafe medical advice from publicly available chatbots, and further work is needed to improve the clinical safety of these powerful tools.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.