Primary Knee| Volume 35, ISSUE 11, P3117-3122, November 2020

Development of Machine Learning Algorithms to Predict Patient Dissatisfaction After Primary Total Knee Arthroplasty



      Postoperative dissatisfaction after primary total knee arthroplasty (TKA) that requires additional care or readmission may impose a significant financial burden to healthcare systems. The purpose of the current study is to develop machine learning algorithms to predict dissatisfaction after TKA.


      A retrospective review of consecutive TKA patients between 2014 and 2016 from 1 large academic and 2 community hospitals was performed. Preoperative variables considered for prediction included demographics, medical history, flexion contracture, knee flexion, and outcome scores (patient-reported health state, Knee Society Score [KSS], and KSS-Function [KSS-F]). Recursive feature elimination was used to select features that optimized algorithm performance. Five supervised machine learning algorithms were developed by training with 10-fold cross-validation 3 times. These algorithms were subsequently applied to an independent testing set of patients and assessed by discrimination, calibration, Brier score, and decision curve analysis.


      Of 430 patients, a total of 40 (9.0%) were dissatisfied with their outcome after primary TKA at a minimum of 2 years postoperatively. The random forest algorithm achieved the best performance in the independent testing set not used for algorithm development (c-statistic: 0.77, calibration intercept: 0.087, calibration slope: 0.74, Brier score: 0.082). The most important factors for predicting dissatisfaction were age, number of medical comorbidities, presence of one or more drug allergies, preoperative patient-reported health state score, and preoperative KSS.


      The current study developed machine learning algorithms based on partially modifiable risk factors for predicting dissatisfaction after TKA. This model demonstrates good discriminative capacity for identifying those at greatest risk for dissatisfaction and may allow for preoperative health optimization.


      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'


      Subscribe to The Journal of Arthroplasty
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Choi Y.J.
        • Ra H.J.
        Patient satisfaction after total knee arthroplasty.
        Knee Surg Relat Res. 2016; 28: 1-15
        • Bourne R.B.
        • Chesworth B.M.
        • Davis A.M.
        • Mahomed N.N.
        • Charron K.D.
        Patient satisfaction after total knee arthroplasty: who is satisfied and who is not?.
        Clin Orthop Relat Res. 2010; 468: 57-63
        • Navarro S.M.
        • Wang E.Y.
        • Haeberle H.S.
        • Mont M.A.
        • Krebs V.E.
        • Patterson B.M.
        • et al.
        Machine learning and primary total knee arthroplasty: patient forecasting for a patient-specific payment model.
        J Arthroplasty. 2018; 33: 3617-3623
        • Karas V.
        • Kildow B.J.
        • Baumgartner B.T.
        • Green C.L.
        • Attarian D.E.
        • Bolognesi M.P.
        • et al.
        Preoperative patient profile in total hip and knee arthroplasty: predictive of increased medicare payments in a bundled payment model.
        J Arthroplasty. 2018; 33 (2728-2733.e2723)
        • Ramkumar P.N.
        • Karnuta J.M.
        • Navarro S.M.
        • Haeberle H.S.
        • Scuderi G.R.
        • Mont M.A.
        • et al.
        Deep learning preoperatively predicts value metrics for primary total knee arthroplasty: development and validation of an artificial neural network model.
        J Arthroplasty. 2019; 34 (2220-2227.e2221)
        • Kunze K.N.
        • Akram F.
        • Fuller B.C.
        • Zabawa L.
        • Sporer S.M.
        • Levine B.R.
        Internal validation of a predictive model for satisfaction after primary total knee arthroplasty.
        J Arthroplasty. 2019; 34: 663-670
        • De Silva A.P.
        • Moreno-Betancur M.
        • De Livera A.M.
        • Lee K.J.
        • Simpson J.A.
        Multiple imputation methods for handling missing values in a longitudinal categorical variable with restrictions on transitions over time: a simulation study.
        BMC Med Res Methodol. 2019; 19: 14
        • Lee K.J.
        • Carlin J.B.
        Multiple imputation in the presence of non-normal data.
        Stat Med. 2017; 36: 606-617
        • Breiman L.
        Random forests.
        Machine Learn. 2001; 45: 5-32
        • Hastie T.
        • Tibshirani R.
        • Friedman J.
        The elements of statistical learning: data mining, inference, and prediction.
        Springer, 2009 ([accessed 10.03.2020])
        • Friedman J.H.
        Stochastic gradient boosting.
        Comput Stat Data Anal. 2002; 38: 367-378
        • Friedman J.
        • Hastie T.
        • Tibshirani R.
        Regularization paths for generalized linear models via coordinate descent.
        J Stat Softw. 2010; 33: 1-22
        • Greenwell B.M.
        • Boehmke B.C.
        • McCarthy A.J.
        A simple and effective model-based variable importance measure: Cornell University.
        ([accessed 04.03.2020])
        • Steyerberg E.W.
        • Vergouwe Y.
        Towards better clinical prediction models: seven steps for development and an ABCD for validation.
        Eur Heart J. 2014; 35: 1925-1931
        • Steyerberg E.W.
        • Vickers A.J.
        • Cook N.R.
        • Gerds T.
        • Gonen M.
        • Obuchowski N.
        • et al.
        Assessing the performance of prediction models: a framework for traditional and novel measures.
        Epidemiology. 2010; 21: 128-138
        • Kattan M.W.
        • Gerds T.A.
        The index of prediction accuracy: an intuitive measure useful for evaluating risk prediction models.
        Diagn Progn Res. 2018; 2
        • Brier G.W.
        Verification of forecasts expressed in terms of probability.
        Mon weather Rev. 1950; 78: 1-3
        • Brier G.W.
        • Allen R.A.
        Verification of weather forecasts.
        in: Malone T.F. Compendium of meteorology. American Meteorological Society, Boston, MA1951: 841-848
        • Vickers A.J.
        • Elkin E.B.
        Decision curve analysis: a novel method for evaluating prediction models.
        Med Decis Making. 2006; 26: 565-574
        • Vickers A.J.
        • Cronin A.M.
        • Elkin E.B.
        • Gonen M.
        Extensions to decision curve analysis, a novel method for evaluating diagnostic tests, prediction models and molecular markers.
        BMC Med Inform Decis Mak. 2008; 8: 53
        • Ribeiro M.T.
        • Singh S.
        • Guestrin C.
        Model-agnostic interpretability of machine learning.: Cornell University.
        ([accessed 04.03.2020])
        • Gunaratne R.
        • Pratt D.N.
        • Banda J.
        • Fick D.P.
        • Khan R.J.K.
        • Robertson B.W.
        Patient dissatisfaction following total knee arthroplasty: a systematic review of the literature.
        J Arthroplasty. 2017; 32: 3854-3860
        • Bryan S.
        • Goldsmith L.J.
        • Davis J.C.
        • Hejazi S.
        • MacDonald V.
        • McAllister P.
        • et al.
        Revisiting patient satisfaction following total knee arthroplasty: a longitudinal observational study.
        BMC Musculoskelet Disord. 2018; 19: 423
        • Otero J.E.
        • Graves C.M.
        • Gao Y.
        • Olson T.S.
        • Dickinson C.C.
        • Chalus R.J.
        • et al.
        Patient-reported allergies predict worse outcomes after hip and knee arthroplasty: results from a prospective cohort study.
        J Arthroplasty. 2016; 31: 2746-2749
        • Graves C.M.
        • Otero J.E.
        • Gao Y.
        • Goetz D.D.
        • Willenborg M.D.
        • Callaghan J.J.
        Patient reported allergies are a risk factor for poor outcomes in total hip and knee arthroplasty.
        J Arthroplasty. 2014; 29: 147-149
        • Kunze K.N.
        • Karhade A.V.
        • Sadauskas A.J.
        • Schwab J.H.
        • Levine B.R.
        Development of machine learning algorithms to predict clinically meaningful improvement for the patient-reported health state after total hip arthroplasty.
        J Arthroplasty. 2020;
        • Khan O.
        • Badhiwala J.H.
        • Witiw C.D.
        • Wilson J.R.
        • Fehlings M.G.
        Machine learning algorithms for prediction of health-related quality-of-life after surgery for mild degenerative cervical myelopathy.
        Spine J. 2020;
        • Shah A.A.
        • Karhade A.V.
        • Bono C.M.
        • Harris M.B.
        • Nelson S.B.
        • Schwab J.H.
        Development of a machine learning algorithm for prediction of failure of nonoperative management in spinal epidural abscess.
        Spine J. 2019; 19: 1657-1665
        • Karhade A.V.
        • Shah A.A.
        • Bono C.M.
        • Ferrone M.L.
        • Nelson S.B.
        • Schoenfeld A.J.
        • et al.
        Development of machine learning algorithms for prediction of mortality in spinal epidural abscess.
        Spine J. 2019; 19: 1950-1959