Comparisons of machine learning models to logistic regression in orthopedic sports medicine are confounded by methodological heterogeneity: a systematic review and meta-analysis

UT Southwestern researchers from the Department of Orthopaedic Surgery systematically reviewed machine learning (ML) prediction models in orthopaedic sports medicine, comparing their performance with traditional logistic regression methods. The study found that random forest algorithms often outperformed conventional statistical approaches in well-designed studies, though current evidence does not yet establish ML as definitively superior to traditional models.