ArticleMayo Clinic proceedings. Digital health2023
Learning to Fake It: Limited Responses and Fabricated References Provided by ChatGPT for Medical Questions.
Article in Mayo Clinic proceedings. Digital health, 2023. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 78 papers, 3 of them syntheses that pooled it.
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
78 citing papers in PubMed, 3 syntheses or guidelines pooled it.
- Improvement of Clinical Practice Guideline Appraisal by Human Experts and AI Agents by Using Structured Guidance: Systematic Review, Meta-Analysis, and Validation Study.Journal of medical Internet research · 2026Pooled it
- Large Language Models for Chatbot Health Advice Studies: A Systematic Review.JAMA network open · 2025Pooled it
- Exploring the role of ChatGPT in patient care (diagnosis and treatment) and medical research: A systematic review.Health promotion perspectives · 2023Pooled it
- Evaluation of the applicability of AI chatbots in addressing health management issues for living kidney donors.International urology and nephrology · 2026Article
- Authors, reviewers, editors… smitten and bitten by the artificial intelligence (AI) bug!Indian journal of anaesthesia · 2026Article
- Leveraging generative artificial intelligence errors to teach appropriate citation usage.Journal of microbiology & biology education · 2026Article
- Harnessing AI and chatbots to develop an interactive learning activity: student perceptions and outcomes.Journal of microbiology & biology education · 2026Article
- Teaching the Atomic Sentence Method for Source-Verified, AI-Assisted Literature Synthesis to Clinical Health Care Professionals: Single-Cohort Feasibility and Acceptability Study.JMIR formative research · 2026Article
- Prompt Framing and Evidence Requirement for AI-Generated Educational Responses in Dental Education: Experimental Study.JMIR medical education · 2026Article
- High Accuracy, Questionable References: Large Language Models' Performance and Citation Reliability in Foot and Ankle Surgery Examinations.Foot & ankle orthopaedics · 2026Article
- A reproducible statistical evaluation framework for large-sample assessment of AI-generated medical references: cross-platform application of the reference hallucination score.BMC medical research methodology · 2026Article
- Performance of large language models in interpreting evidence-based clinical guidelines for lumbar disc herniation with radiculopathy.European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society · 2026Article
- Arkangel AI, OpenEvidence, ChatGPT, Medisearch: Are They Objectively up to Medical Standards? A Real-Life Assessment of LLM Chatbots in Health Care.Mayo Clinic proceedings. Digital health · 2026Article
- Coconstructing CHAMP, an Artificial Intelligence Chatbot for Pediatric Infectious Symptoms Management: Protocol for a Multiphase Participatory Study.JMIR research protocols · 2026Article
- Evaluation of Arabic-Language AI Chatbot Responses to Migraine-Related Questions: A Comparative Cross-Sectional Study.Journal of clinical medicine · 2026Article
- A scoping review of guides and advice for scholarly citing in health research.Research integrity and peer review · 2026Review
- Multidimensional evaluation of large language models on the AAP in-service examination: Assessing accuracy, calibration, and citation reliability.PLOS digital health · 2026Article
- Can Large Artificial Intelligence-Based Linguistic Models Help to Obtain Information About Burning Mouth Syndrome?Oral diseases · 2026Article
- Medicine digital transformation: evidence from Chinese physicians on generative artificial intelligence implementation and challenges.Journal of translational medicine · 2026Article
- Performance Evaluation of Large Language Models in Multilingual Medical Multiple-Choice Questions: Mixed Methods Study.JMIR medical education · 2026Article
18 more citing papers are in PubMed but not listed here.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
3 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Objective: To evaluate the quality of the answers and the references provided by ChatGPT for medical questions. Patients and Methods: Three researchers asked ChatGPT 20 medical questions and prompted it to provide the corresponding references. The responses were evaluated for the quality of content by medical experts using a verbal numeric scale going from 0% to 100%. These experts were the corresponding authors of the 20 articles from where the medical questions were derived. We planned to evaluate 3 references per response for their pertinence, but this was amended on the basis of preliminary results showing that most references provided by ChatGPT were fabricated. This experimental observational study was conducted in February 2023. Results: ChatGPT provided responses varying between 53 and 244 words long and reported 2 to 7 references per answer. Seventeen of the 20 invited raters provided feedback. The raters reported limited quality of the responses, with a median score of 60% (first and third quartiles: 50% and 85%, respectively). In addition, they identified major (n=5) and minor (n=7) factual errors among the 17 evaluated responses. Of the 59 references evaluated, 41 (69%) were fabricated, although they appeared real. Most fabricated citations used names of authors with previous relevant publications, a title that seemed pertinent and a credible journal format. Conclusion: When asked multiple medical questions, ChatGPT provided answers of limited quality for scientific publication. More importantly, ChatGPT provided deceptively real references. Users of ChatGPT should pay particular attention to the references provided before integration into medical manuscripts.
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.