Preoperative MRI and machine learning predict meniscal repairability with AUC 0.78

A machine learning model using preoperative MRI and clinical features predicted meniscal repairability at arthroscopy with an AUC of 0.78 (95% CI 0.74-0.82) in a retrospective cohort of 491 patients. Independent predictors of non-repairability included ACL injury, cartilage dege…

• Retrospective cohort of 491 patients who underwent knee MRI and subsequent arthroscopy.
• Logistic regression performed best (AUC 0.78), with good calibration and decision curve benefit.
• Key predictors of non-repairability: ACL injury, high-grade cartilage degeneration, ≥3 mm tear displacement, male sex, and higher BMI.

Abstract only; full-text not reviewed.

Automated summary

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