Machine Learning Predicts Femoral and Tibial Implant Size Mismatch for Total Knee Arthroplasty

Abstract

Background: Despite reasonable accuracy with preoperative templating, the search for an optimal planning tool remains an unsolved dilemma. The purpose of the present study was to apply machine learning (ML) using preoperative demographic variables to predict mismatch between templating and final component size in primary total knee arthroplasty (TKA) cases. Methods: This was a retrospective case-control study of primary TKA patients between September 2012 and April 2018. The primary outcome was mismatch between the templated and final implanted component sizes extracted from the operative database. The secondary outcome was mismatch categorized as undersized and oversized. Five supervised ML algorithms were trained using 6 demographic features. Prediction accuracies were obtained as a metric of performance for binary mismatch (yes/no) and multilevel (undersized/correct/oversized) classifications. Results: A total of 1801 patients were included. For binary classification, the best-performing algorithm for predicting femoral and tibial mismatch was the stochastic gradient boosting model (area under the curve: 0.76/0.72, calibration intercepts: 0.05/0.05, calibration slopes: 0.55/0.7, and Brier scores: 0.20/0.21). For multiclass classification, the best-performing algorithms had accuracies of 83.9% and 82.9% for predicting the concordance/mismatch of the femoral and tibial implant, respectively. Model predictions of greater than 51.0% and 47.9% represented high-risk thresholds for femoral and tibial sizing mismatch, respectively. Conclusions: ML algorithms predicted templating mismatch with good accuracy. External validation is necessary to confirm the performance and reliability of these algorithms. Predicting sizing mismatch is the first step in using ML to aid in the prediction of final TKA component sizes. Further studies to optimize parameters and predictions for the algorithms are ongoing.

Machine learning algorithms predict within one size of the final implant ultimately used in total knee arthroplasty with good-to-excellent accuracy

“…These potential benefits have been recognized by other knee surgeons, as recent literature has sought to leverage the personalization and predictive capabilities of machine learning toward similar goals [16, 35]. Polce et al applied machine learning to predict a mismatch between digitally templated TKA sizes and the final implant sizes that were used at the time of surgery in a consecutive series of 1,801 patients [22]. Their best performing models were found to predict patients at greater risk for mismatch between preoperative templating and final femoral and tibial implant sizes with acceptable to good predictive performance.…”

Machine Learning for the Orthopaedic Surgeon

“…In total knee arthroplasty, even with diligent preoperative templating, there can be a mismatch between the planned and final implant sizes 44 . Polce et al successfully utilized ML to predict, with high accuracy, the concordance or mismatch of the femoral and tibial implants for 1,801 patients 45 .…”

Meaningless Applications and Misguided Methodologies in Artificial Intelligence–Related Orthopaedic Research Propagates Hype Over Hope

“…or "AI predicts..". [23][24][25][26][27][28] This portrayal is closer to marketing than science and underscores a fundamentally misunderstood tenet: AI is only as good as the data that fuel its process. The bottleneck of AI-derived insights is not the analytic process, but rather the quality of the data.…”