Abstract
Objectives:
Previous machine learning (ML) analysis of national ligament registries found moderate accuracy for predicting ACL reconstruction revision risk. We examine whether an enhanced ML-Cox regression approach can improve the prediction accuracy for ACL reconstruction revision using data from the Danish Knee Ligament Reconstruction Registry (DKRR).
Methods:
Data was extracted from the DKRR on all patients who underwent primary ACL reconstruction between 2005 and 2023. An enhanced ML approach using Cox regression with a least absolute shrinkage and selection operator (LASSO) penalised approach and stable iterative variable selection (SIVS) was applied using a multi-stage analysis. The most significant demographic, clinical and PROM data from this analysis of the DKRR were selected for the final Cox regression model. Data was randomly split in a 2:1 ratio into separate training and test cohorts for developing and internally validating regression models, respectively.
Results:
The best performing Cox regression model for predicting ACL reconstruction revision risk incorporated age (at time of primary ACL reconstruction), Pain P1 and QoL Q2 and Q3, from 12-month follow-up KOOS data. This model demonstrated good prediction accuracy 1 year (C-index=0.739 ± 0.027), 2 years (C-index=0.735 ± 0.020), and 5 years (C-index=0.727 ± 0.016) after 12-month follow-up assessment.
We developed an online clinical tool (DK3 – Clinical Readiness Tool) for predicting risk and modified risk of ACL reconstruction revision at a patient-specific level. Using the DK3 to predict the risk of a 25 year-old patient with KOOS values of 2 for P1, Q2 & Q3 gives a predicted risk of ACL reconstruction revision of 2.9% (1 year), 5.2% (2 years) and 9.2% (5 years) after 12-month follow-up assessment. Using the risk modification option to adjust the KOOS values to 0 (i.e. normal) reduces the predicted risk to 0.8% (1 year), 1.5% (2 years) and 2.7% (5 years).
Conclusion:
An enhanced ML-Cox regression using patient age and 3 KOOS items obtained 12-months post-surgery provided good prediction accuracy of ACL reconstruction revision risk at 1, 2 and 5 years relative to 12-month follow-up assessment. The current modelling demonstrated greater prediction accuracy, requiring fewer input variables, compared to a previous ML study incorporating pre-operative data. The DK3 - Clinical Readiness Tool can be used to assess patient-specific ACL reconstruction revision and modified risk. This information can be used to guide patient rehabilitation and clinical management if required.