Machine Learning and Primary Total Knee Arthroplasty: Patient Forecasting for a Patient-Specific Payment Model

Background: Value-based and patient-specific care represent 2 critical areas of focus that have yet to be fully reconciled by today's bundled care model. Using a predictive naïve Bayesian model, the objectives of this study were (1) to develop a machine-learning algorithm using preoperative big data to predict length of stay (LOS) and inpatient costs after primary total knee arthroplasty (TKA) and (2) to propose a tiered patient-specific payment model that reflects patient complexity for reimbursement.

Methods: Using 141,446 patients undergoing primary TKA from an administrative database from 2009 to 2016, a Bayesian model was created and trained to forecast LOS and cost. Algorithm performance was determined using the area under the receiver operating characteristic curve and the percent accuracy. A proposed risk-based patient-specific payment model was derived based on outputs.

Results: The machine-learning algorithm required age, race, gender, and comorbidity scores ("risk of illness" and "risk of morbidity") to demonstrate a high degree of validity with an area under the receiver operating characteristic curve of 0.7822 and 0.7382 for LOS and cost. As patient complexity increased, cost add-ons increased in tiers of 3%, 10%, and 15% for moderate, major, and extreme mortality risks, respectively.

Conclusion: Our machine-learning algorithm derived from an administrative database demonstrated excellent validity in predicting LOS and costs before primary TKA and has broad value-based applications, including a risk-based patient-specific payment model.