ArticleThe Iowa orthopaedic journal2025
Evaluating if ChatGPT Can Answer Common Patient Questions Compared to OrthoInfo Regarding Lateral Epicondylitis.
Article in The Iowa orthopaedic journal, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 1 paper.
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
1 citing paper in PubMed.
- Prompt Framing Modulates Safety in Shoulder and Elbow Red-Flag Vignettes: A Large Language Model Study.Diagnostics (Basel, Switzerland) · 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
7 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Background: As online medical resources become more accessible, patients increasingly consult AI platforms like ChatGPT for health-related information. Our study assessed the accuracy and appropriateness of ChatGPT's responses to common questions about lateral epicondylitis, comparing them against OrthoInfo as a gold standard. Methods: Eight frequently asked questions about lateral epicondylitis from OrthoInfo were selected and presented to ChatGPT at both standard and sixth-grade reading levels. Responses were evaluated for accuracy and appropriateness using a five-point Likert scale, with scores of four or above deemed satisfactory. Evaluations were conducted by two fellowship-trained Shoulder and Elbow surgeons, two Hand surgeons, and one Orthopaedic Sports fellow. We utilized the Flesch-Kincaid test to assess readability, and responses were statistically analyzed using paired t-tests. Results: ChatGPT's responses at the sixth-grade level scored lower in accuracy (mean = 3.9 ± 0.87, p = 0.046) and appropriateness (mean = 3.7 ± 0.92, p = 0.045) compared to the standard level (accuracy = 4.7 ± 0.43, appropriateness = 4.7 ± 0.45). When compared with OrthoInfo, standard responses from ChatGPT showed significantly lower accuracy (mean difference = -0.275, p = 0.004) and appropriateness (mean difference = -0.475, p = 0.016). The Flesch-Kincaid grade level was significantly higher in the standard response group (mean = 14.06, p < 0.001) compared to both OrthoInfo (mean = 8.98) and the sixth-grade responses (mean = 8.48). No significance was noted between the Flesch-Kincaid grades of OrthoInfo and the sixth-grade responses. Conclusion: At a sixth-grade reading level, Chat-GPT provides oversimplified and less accurate information regarding lateral epicondylitis. Although standard level responses are more accurate, they still do not meet the reliability of OrthoInfo and exceed the recommended readability for patient education materials. While ChatGPT cannot be recommended as a sole information source, it may serve as a supplementary resource alongside professional medical consultation.
Indexed as
Identifiers
40606724PMC12212301What 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.