Transparency of reporting and methodological conduct of prognostic and diagnostic clinical prediction models developed using machine learning in total shoulder arthroplasty: A systematic review and critical appraisal

Puntos clave

• AI prediction models in total shoulder arthroplasty demonstrate significant methodological flaws, particularly in calibration and validation.
• Only a limited number of studies adequately report sample size and missing data issues, raising concerns about their reliability.
• Systematic review analysis covers various studies rated from level I to IV, highlighting common deficiencies across the board.
• Overall, the findings indicate a pressing need for clearer reporting standards to ensure accurate clinical applications of these models.