Predicting the Risk of Posttraumatic Osteoarthritis After Primary Anterior Cruciate Ligament Reconstruction: A Machine Learning Time-to-Event Analysis

Abstract

Background:

There is a significant long-term risk of posttraumatic osteoarthritis (PTOA) after anterior cruciate ligament reconstruction (ACLR). Elucidating the risk factors and successfully identifying at-risk patients is challenging.

Purpose/Hypothesis:

The purpose of this study was to produce machine learning survival models that can identify (1) patients at risk of symptomatic PTOA and (2) patients who are at risk of undergoing total knee arthroplasty (TKA) after ACLR. It was hypothesized that these models would outperform traditional Kaplan-Meier estimators.

Study Design:

Case-control study; Level of evidence, 3.

Methods:

A geographic database was used to identify patients undergoing ACLR between 1990 and 2016 with a minimum 7.5-year follow-up. Models were used to analyze various factors to predict the rate and time to (1) symptomatic osteoarthritis and (2) TKA using random survival forest (RSF) algorithms. Performance was measured using out-of-bag (OOB) c-statistic, calibration, and Brier score. The predictive performances of the RSF models were compared with Kaplan-Meier estimators. Model interpretability was enhanced utilizing global variable importance and partial dependence curves.

Results:

A total of 974 patients with ACLR and a minimum follow-up of 7.5 years were included; among these, 215 (22.1%) developed symptomatic osteoarthritis, and 25 (2.6%) progressed to TKA. The RSF algorithms achieved acceptable good to excellent predictive performance for symptomatic arthritis (OOB c-statistic, 0.75; Brier score, 0.128) and progression to TKA (OOB c-statistic, 0.89; Brier score, 0.026), respectively. Significant predictors of symptomatic PTOA included increased pain scores, older age, increased body mass index, increased time to ACLR, total number of arthroscopic surgeries before the diagnosis of arthritis, positive pivot-shift test after reconstruction, concomitant chondral injury, secondary meniscal tear, early (<250 days) or delayed (>500 days) return to sports or activity, and use of allograft. Significant predictors for TKA included older age, increased pain scores, total number of arthroscopic surgeries, high-demand activity/occupation, hypermobility, higher body mass index, systemic inflammatory disease, increased time to surgery, early (<250 days) or delayed (>500 days) return to sports or activity, and midsubstance tears. The Brier score over time revealed that RSF models outperformed traditional Kaplan-Meier estimators.

Conclusion:

Machine learning survival models were used to reliably identify patients at risk of developing symptomatic PTOA, and these models consistently outperformed traditional Kaplan-Meier estimators. Strong predictors for the development of PTOA after ACLR included increased pain scores at injury and postoperative visit, older age at injury, total number of arthroscopic procedures, positive postoperative pivot-shift test, and secondary meniscal tear.