Artificial intelligence in ultrasound imaging for carpal tunnel syndrome: what clinicians need to know

This review examines artificial intelligence (AI) applications in ultrasound imaging for carpal tunnel syndrome diagnosis. Deep learning models have achieved Dice coefficients exceeding 0.85 for median nerve segmentation and diagnostic accuracy with area under the curve values up to 0.926, often matching specialist performance. However, methodological limitations exist: only three of 13 included studies (23%) performed external validation, and most used single-center retrospective designs. No prospective clinical trials have demonstrated improved patient outcomes. We critically appraise study quality, discuss current limitations, and provide practical recommendations for clinicians considering AI integration into their practice.