AI-assisted pediatric fracture detection in the ED: small, non-significant reduction in diagnostic revisions and patient recalls

AI-assisted fracture detection in a pediatric emergency setting reduced diagnostic revisions from 8.6% to 5.7% (RR 0.66, 95% CI 0.37–1.19), but the reduction was not statistically significant. No improvement in therapeutic changes, length of stay, or diagnostic confidence.

• Diagnostic revision rate was 5.7% with AI vs 8.6% without (RR 0.66, 95% CI 0.37–1.19, not significant).
• No significant differences in therapeutic changes, need for senior consultation, diagnostic confidence, or length of stay.
• The small effect size and limited impact on clinical outcomes raise questions about the practical benefit of AI-assisted fracture detection in this setting.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.