Summary

The prediction model of this study showed the feasibility of using machine learning models as a supplementary diagnostic tool for ramp lesions in ACL-injured knees.

Abstract

Background

Peripheral tears of the posterior horn medial meniscus, known as “ramp lesions,” are commonly found in anterior cruciate ligament (ACL)-deficient knees, but frequently missed on routine evaluation.

Purpose

To predict the presence of ramp lesions in ACL-deficient knees using machine learning methods with associated risk factors.

Methods

This study included 362 patients who underwent ACL reconstruction between June 2013 and March 2019. The exclusion criteria were combined fractures and multiple ligament injuries, except for medial collateral ligament injury. Patients were grouped according to the presence of ramp lesions by arthroscopy. Binary logistic regression was used to analyze risk factors including age, sex, body mass index, time from injury (>3 or <3 months), mechanism of injury (contact or non-contact), side-to-side laxity, grade of pivot shift, medial and lateral tibial/meniscal slope, location of bone contusion, mechanical axis angle, and lateral femoral condylar (LFC) ratio. Receiver-operating characteristic (ROC) curves and area under the curve (AUC) were also evaluated.

Results

Ramp lesions were identified in 112 patients (30.9%). The risk for ramp lesions increased with a steeper medial tibial and meniscal slope, higher knee laxity, and increased LFC ratio. Comparing the final performance of all prediction models, the random forest model yielded the best performance (AUC=0.944), although there were no significant differences among the models (p>0.05). The cut-off values for ramp lesions in ROC analysis were as follows: medial tibial slope >5.5° (p<0.001); medial meniscal slope >5.0° (p<0.001); and LFC ratio >71.1% (p=0.033).

Conclusion

A steep medial tibial and meniscal slope, an increased LFC depth and a higher knee rotational laxity were observed risk factors for ramp lesions in patients with an ACL injury. The prediction model of this study showed the feasibility of using machine learning models as a supplementary diagnostic tool for ramp lesions in ACL-injured knees. In general, care should be taken in patients with ramp lesions and risk factors during ACL reconstruction.