Identifying Modifiable Cost Drivers of Outpatient Unicompartmental Knee Arthroplasty With Machine Learning

Published:October 17, 2022DOI:



      Implementing tools that identify cost-saving opportunities for ambulatory orthopaedic surgeries can improve access to value-based care. We developed and internally validated a machine learning (ML) algorithm to predict cost drivers of total charges after ambulatory unicompartmental knee arthroplasty (UKA).


      We queried the New York State Ambulatory Surgery and Services database to identify patients who underwent ambulatory, defined as <24 hours of care before discharge, elective UKA between 2014 and 2016. A total of 1,311 patients were included. The median costs after ambulatory UKA were $14,710. Patient demographics and intraoperative parameters were entered into 4 candidate ML algorithms. The most predictive model was selected following internal validation of candidate models, with conventional linear regression as a benchmark. Global variable importance and partial dependence curves were constructed to determine the impact of each input parameter on total charges.


      The gradient-boosted ensemble model outperformed all candidate algorithms and conventional linear regression. The major differential cost drivers of UKA identified (in decreasing order of magnitude) were increased operating room time, length of stay, use of regional and adjunctive periarticular analgesia, utilization of computer-assisted navigation, and routinely sending resected tissue to pathology.


      We developed and internally validated a supervised ML algorithm that identified operating room time, length of stay, use of computer-assisted navigation, regional primary anesthesia, adjunct periarticular analgesia, and routine surgical pathology as essential cost drivers of UKA. Following external validation, this tool may enable surgeons and health insurance providers optimize the delivery of value-based care to patients receiving outpatient UKA.

      Level of Evidence



      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


        • Newman J.
        • Pydisetty R.V.
        • Ackroyd C.
        Unicompartmental or total knee replacement: the 15-year results of a prospective randomised controlled trial.
        J Bone Joint Surg Br. 2009; 91: 52-57
        • Price A.J.
        • Webb J.
        • Topf H.
        • Dodd C.A.
        • Goodfellow J.W.
        • Murray D.W.
        Rapid recovery after oxford unicompartmental arthroplasty through a short incision.
        J Arthroplasty. 2001; 16: 970-976
        • Jensen C.B.
        • Petersen P.B.
        • Jørgensen C.C.
        • Kehlet H.
        • Troelsen A.
        • Gromov K.
        Length of stay and 90-day readmission/complication rates in unicompartmental versus total knee arthroplasty: a propensity-score-matched study of 10,494 procedures performed in a fast-track setup.
        J Bone Joint Surg Am. 2021; 103: 1063-1071
        • Ford M.C.
        • Walters J.D.
        • Mulligan R.P.
        • Dabov G.D.
        • Mihalko W.M.
        • Mascioli A.M.
        • et al.
        Safety and cost-effectiveness of outpatient unicompartmental knee arthroplasty in the ambulatory surgery center: a matched cohort study.
        Orthop Clin North Am. 2020; 51: 1-5
        • Kahlenberg C.A.
        • Richardson S.S.
        • Gruskay J.A.
        • Cross M.B.
        Trends in utilization of total and unicompartmental knee arthroplasty in the United States.
        J Knee Surg. 2021; 34: 1138-1141
        • Arshi A.
        • Wellens B.
        • Krueger C.A.
        The changing economic value and leverage of arthroplasty surgeons: how the shift in arthroplasty surgery location impacts the relationship of private surgeons, hospitals, and ambulatory surgery centers.
        J Arthroplasty. 2021; 37: 1455-1458
        • Yayac M.
        • Schiller N.
        • Austin M.S.
        • Courtney P.M.
        2020 John N. Insall Award: removal of total knee arthroplasty from the inpatient-only list adversely affects bundled payment programmes.
        Bone Joint J. 2020; 102-B: 19-23
        • Curtin B.M.
        • Odum S.M.
        Unintended bundled payments for care improvement consequences after removal of total knee arthroplasty from inpatient-only list.
        J Arthroplasty. 2019; 34: S121-S124
        • Collins G.S.
        • Reitsma J.B.
        • Altman D.G.
        • Moons K.G.
        Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement.
        BMJ. 2015; 350: g7594
        • Luo W.
        • Phung D.
        • Tran T.
        • Gupta S.
        • Rana S.
        • Karmakar C.
        • et al.
        Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view.
        J Med Internet Res. 2016; 18: e323
      1. Healthcare Cost and Utilization Project (HCUP) Statistical Briefs. Agency for Healthcare Research and Quality (US), Rockville (MD)2006
        • Statistics UBoL
        Consumer price index archived news releases.
        ([accessed 20.01.21])
        • Elixhauser A.
        • Steiner C.
        • Harris D.R.
        • Coffey R.M.
        Comorbidity measures for use with administrative data.
        Med Care. 1998; 36: 8-27
        • Stekhoven D.J.
        • Bühlmann P.
        MissForest--non-parametric missing value imputation for mixed-type data.
        Bioinformatics. 2012; 28: 112-118
        • Armstrong R.A.
        When to use the Bonferroni correction.
        Ophthalmic Physiol Opt. 2014; 34: 502-508
        • Steyerberg E.W.
        • Moons K.G.
        • van der Windt D.A.
        • Hayden J.A.
        • Perel P.
        • Schroter S.
        • et al.
        Prognosis Research Strategy (PROGRESS) 3: prognostic model research.
        PLoS Med. 2013; 10: e1001381
        • Muhlestein W.E.
        • Akagi D.S.
        • McManus A.R.
        • Chambless L.B.
        Machine learning ensemble models predict total charges and drivers of cost for transsphenoidal surgery for pituitary tumor.
        J Neurosurg. 2018; 131: 507-516
        • Legates D.R.
        • McCabe Jr., G.J.
        Evaluating the use of “goodness-of-fit” Measures in hydrologic and hydroclimatic model validation.
        Water Resour Res. 1999; 35: 233-241
        • Lu Y.
        • Kunze K.
        • Cohn M.R.
        • Lavoie-Gagne O.
        • Polce E.
        • Nwachukwu B.U.
        • et al.
        Artificial intelligence predicts cost after ambulatory anterior cruciate ligament reconstruction.
        Arthrosc Sports Med Rehabil. 2021; 3: e2033-e2045
        • Fabricant P.D.
        • Seeley M.A.
        • Rozell J.C.
        • Fieldston E.
        • Flynn J.M.
        • Wells L.M.
        • et al.
        Cost savings from utilization of an ambulatory surgery center for orthopaedic day surgery.
        J Am Acad Orthop Surg. 2016; 24: 865-871
        • Iweala U.
        • Lee D.
        • Lee R.
        • Weinreb J.H.
        • O'Brien J.R.
        • Yu W.
        Characterizing efficiency in the ambulatory surgery setting: an analysis of operating room time and cost savings in orthopaedic surgery.
        J Orthop. 2019; 16: 534-554
        • Huynh E.
        • Klouche S.
        • Martinet C.
        • Le Mercier F.
        • Bauer T.
        • Lecoeur A.
        Can the number of surgery delays and postponements due to unavailable instrumentation be reduced? Evaluating the benefits of enhanced collaboration between the sterilization and orthopedic surgery units.
        Orthop Traumatol Surg Res. 2019; 105: 563-568
        • Karvonen S.
        • Nordback I.
        • Elo J.
        • Havulinna J.
        • Laine H.J.
        The elimination of transfer distances is an important part of hospital design.
        HERD. 2017; 10: 142-151
        • Tayne S.
        • Merrill C.A.
        • Saxena R.C.
        • King C.
        • Devarajan K.
        • Ianchulev S.
        • et al.
        Maximizing operational efficiency using an in-house ambulatory surgery model at an academic medical center.
        J Healthc Manag. 2018; 63: 118-129
        • Moore J.G.
        • Ross S.M.
        • Williams B.A.
        Regional anesthesia and ambulatory surgery.
        Curr Opin Anaesthesiol. 2013; 26: 652-660
        • Mittal A.
        • Meshram P.
        • Kim T.K.
        What is the evidence for clinical use of advanced technology in unicompartmental knee arthroplasty?.
        Int J Med Robot. 2021; 17: e2302
        • Novak E.J.
        • Silverstein M.D.
        • Bozic K.J.
        The cost-effectiveness of computer-assisted navigation in total knee arthroplasty.
        J Bone Joint Surg Am. 2007; 89: 2389-2397
        • Robinson P.G.
        • Clement N.D.
        • Hamilton D.
        • Blyth M.J.G.
        • Haddad F.S.
        • Patton J.T.
        A systematic review of robotic-assisted unicompartmental knee arthroplasty: prosthesis design and type should be reported.
        Bone Joint J. 2019; 101-B: 838-847
        • Pagnano M.W.
        • Forero J.H.
        • Scuderi G.R.
        • Harwin S.F.
        Is the routine examination of surgical specimens worthwhile in primary total knee arthroplasty?.
        Clin Orthop Relat Res. 1998; : 79-84
        • Kocher M.S.
        • Erens G.
        • Thornhill T.S.
        • Ready J.E.
        Cost and effectiveness of routine pathological examination of operative specimens obtained during primary total hip and knee replacement in patients with osteoarthritis.
        J Bone Joint Surg Am. 2000; 82: 1531-1535
      2. State ambulatory surgery and services database.
        ([accessed 30.08.22])

      Supplemental References

        • Hughes J.D.
        • Hughes J.L.
        • Bartley J.H.
        • Hamilton W.P.
        • Brennan K.L.
        Infection rates in arthroscopic versus open rotator cuff repair.
        Orthop J Sports Med. 2017; 5 (2325967117715416)
        • Huque M.H.
        • Carlin J.B.
        • Simpson J.A.
        • Lee K.J.
        A comparison of multiple imputation methods for missing data in longitudinal studies.
        BMC Med Res Methodol. 2018; 18: 168
        • Stekhoven D.J.
        • Bühlmann P.
        MissForest--non-parametric missing value imputation for mixed-type data.
        Bioinformatics. 2012; 28: 112-118
        • Sterne J.A.C.
        • White I.R.
        • Carlin J.B.
        • Spratt M.
        • Royston P.
        • Kenward M.G.
        • et al.
        Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls.
        BMJ. 2009; 338: b2393
        • Moons K.G.
        • Donders R.A.
        • Stijnen T.
        • Harrell Jr., F.E.
        Using the outcome for imputation of missing predictor values was preferred.
        J Clin Epidemiol. 2006; 59: 1092-1101
        • Pedersen A.B.
        • Mikkelsen E.M.
        • Cronin-Fenton D.
        • Kristensen N.R.
        • Pham T.M.
        • Pedersen L.
        • et al.
        Missing data and multiple imputation in clinical epidemiological research.
        Clin Epidemiol. 2017; 9: 157-166
        • Karhade A.V.
        • Ogink P.T.
        • Thio Q.
        • Broekman M.L.D.
        • Cha T.D.
        • Hershman S.H.
        • et al.
        Machine learning for prediction of sustained opioid prescription after anterior cervical discectomy and fusion.
        Spine J. 2019; 19: 976-983
        • Raschka S.
        Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning.
        2018 (arXiv preprint arXiv:1811.12808) ([accessed 30.08.22])
        • Steyerberg E.W.
        • Moons K.G.
        • van der Windt D.A.
        • Hayden J.A.
        • Perel P.
        • Schroter S.
        • et al.
        Prognosis Research Strategy (PROGRESS) 3: prognostic model research.
        PLoS Med. 2013; 10: e1001381
        • Dietterich T.G.
        Ensemble Methods in Machine Learning.
        in: Multiple Classifier Systems. MCS 2000. vol 1857. Springer, Berlin, Heidelberg2000
        • Nguyen C.D.
        • Carlin J.B.
        • Lee K.J.
        Model checking in multiple imputation: an overview and case study.
        Emerg Themes Epidemiol. 2017; 14: 8
        • Kuhn M.
        • Johnson K.
        Applied predictive modeling. 26. Springer, Berlin, Heidelberg2013