What question did this study set out to answer?

This study aims to evaluate the accuracy and readability of ChatGPT's responses to pediatric sports medicine questions.

Pandora’s Box of Pediatric Sports Medicine: Assessing ChatGPT Responses to Patient-Centered Questions in Pediatric Sports Medicine

View Full Paper

Ask AI

Bookmark

This study aims to evaluate the accuracy and readability of ChatGPT's responses to pediatric sports medicine questions.
Five frequently asked questions and eight complex clinical questions were posed to ChatGPT.
Responses were scored by four board-certified pediatric orthopaedic surgeons and two clinical fellows on accuracy, relevance, and clarity.
Statistical analyses included Shapiro-Wilk test, Mann Whitney U test, one-way ANOVA, and Kruskal-Wallis test.
ChatGPT's responses had a mean Flesch-Kincaid Grade Level of 15.4 and median Flesch Reading Ease of 23.6.
Moderate agreement among raters was observed, with KCC at 0.57 and a weighted Cohen kappa coefficient of 0.298.
Significantly higher scores were given for PFI and FAQs, with clarity above 4.0 across most questions.

No takes yet. Share an insight, caveat, or question.

Randomized trial evaluates ChatGPT’s accuracy and readability in pediatric sports medicine, suggesting its potential usefulness.

Kebeh et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark