Evaluating if ChatGPT Can Answer Common Patient Questions Compared to OrthoInfo Regarding Lateral Epicondylitis

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.

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.

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.

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. Level of Evidence: IV.