Management of lower extremity traumas: Comparing appropriate use criteria ChatGPT recommendations

Abstract

Background

High-energy lower extremity injury presents with difficult clinical decisions because successful limb salvage is the best scenario for complex traumas, but early amputation may be necessary to limit complications. Artificial Intelligence is a tool rising in popularity to help make clinical judgements.

Purpose/questions

The aim of this study is to determine whether ChatGPT-4 can produce accurate recommendations for limb salvage or amputation given various patient scenarios.

Methods

Various lower leg trauma scenarios were given to the appropriate use criteria for limb salvage made by AAOS or ChatGPT-4. A recommendation score for limb salvage and early amputation were collected. Tests to determine statistical significance between AAOS and ChatGPT-4 were performed.

Results

A total of 196 patient scenario combinations were utilized. The mean error for limb salvage and early amputation were −0.3 and −0.2 respectively. AAOS and ChatGPT had significant positive correlations when predicting limb salvage and early amputation scores. The effect size of limb salvage and early amputation was −0.094 and −0.14, respectively.

Conclusion

ChatGPT-4 generally under-estimates appropriateness scores for both limb salvage and early amputation treatment options, but produces similar scores. ChatGPT-4 may be used to aid physicians in choosing between limb salvage and early amputation, though with caution.