Skip to main content

Advertisement

SpringerLink
Log in

Validation and performance of a machine-learning derived prediction guide for total knee arthroplasty component sizing

  • Knee Arthroplasty
  • Published:
Archives of Orthopaedic and Trauma Surgery Aims and scope Submit manuscript

Abstract

Introduction

Anticipation of patient-specific component sizes prior to total knee arthroplasty (TKA) is essential to avoid excessive cost associated with additional surgical trays and morbidity associated with imperfect sizing. Current methods of size prediction, including templating, are inconsistent and time-consuming. Machine learning (ML) algorithms may allow for accurate TKA component size prediction with the ability to make predictions in real-time.

Methods

Consecutive patients receiving primary TKA between 2012 and 2020 from two large tertiary academic and six community hospitals were identified. The primary outcomes were the final femoral and tibial component sizes extracted from automated inventory systems. Five ML algorithms were trained with routinely corrected demographic variables (age, height, weight, body mass index, and sex) using 80% of the study population and internally validated on an independent set of the remaining 20% of patients. Algorithm performance was evaluated through accuracy, mean absolute error (MAE), and root mean-squared error (RMSE).

Results

A total of 17,283 patients that received one of 9 TKA implants from independent manufacturers were included. The SGB model accuracy for predicting ± 4-mm of the true femoral anteroposterior diameter was 83.6% and for ± 1 size of the true femoral component size was 95.0%. The SGB model accuracy for predicting ± 4-mm of the true tibial medial/lateral diameter was 83.0% and for ± 1 size of the true tibial component size was 97.8%. Patient sex was the most influential feature in terms of informing the SGB model predictions for both femoral and tibial component sizing. A TKA implant sizing application was subsequently created.

Conclusion

Novel machine learning algorithms demonstrated good to excellent performance for predicting TKA component size. Patient sex appears to contribute an important role in predicting TKA size. A web-based real-time prediction application was created capable of integrating patient specific data to predict TKA size, which will require external validation prior to clinical use.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  1. Tang A, Yeroushalmi D, Zak S, Lygrisse K, Schwarzkopf R, Meftah M (2020) The effect of implant size difference on patient outcomes and failure after bilateral simultaneous total knee arthroplasty. J Orthop 22:282–287

    Article  Google Scholar 

  2. Berend ME, Ritter MA, Hyldahl HC, Meding JB, Redelman R (2008) Implant migration and failure in total knee arthroplasty is related to body mass index and tibial component size. J Arthroplasty 23(6 Suppl 1):104–109

    Article  Google Scholar 

  3. Chau R, Gulati A, Pandit H, Beard DJ, Price AJ, Dodd CA, Gill HS, Murray DW (2009) Tibial component overhang following unicompartmental knee replacement–does it matter? Knee 16(5):310–313

    Article  CAS  Google Scholar 

  4. Marmor S, Renault E, Valluy J, Saffarini M (2019) Over-voluming predicted by pre-operative planning in 24% of total knee arthroplasty. Knee Surg Sports Traumatol Arthrosc 27(5):1544–1551

    Article  Google Scholar 

  5. Gonzalez MH, Mekhail AO (2004) The failed total knee arthroplasty: evaluation and etiology. J Am Acad Orthop Surg 12(6):436–446

    Article  Google Scholar 

  6. Trickett RW, Hodgson P, Forster MC, Robertson A (2009) The reliability and accuracy of digital templating in total knee replacement. J Bone Joint Surg Br 91(7):903–906

    Article  CAS  Google Scholar 

  7. Boese CK, Wilhelm S, Haneder S, Lechler P, Eysel P, Bredow J (2019) Influence of calibration on digital templating of hip arthroplasty. Int Orthop 43(8):1799–1805

    Article  Google Scholar 

  8. Sloan M, Premkumar A, Sheth NP (2018) Projected volume of primary total joint arthroplasty in the U.S., 2014 to 2030. J Bone Joint Surg Am 100(17):1455–1460

    Article  Google Scholar 

  9. Polce EM, Kunze KN, Paul K, Levine BR (2021) Machine learning predicts femoral and tibial implant size mismatch for total knee arthroplasty. Arthroplast Today 8:268–277.e2. https://doi.org/10.1016/j.artd.2021.01.006

    Article  PubMed  PubMed Central  Google Scholar 

  10. Bozic KJ, Kamath AF, Ong K, Lau E, Kurtz S, Chan V, Vail TP, Rubash H, Berry DJ (2015) Comparative epidemiology of revision arthroplasty: failed THA poses greater clinical and economic burdens than failed TKA. Clin Orthop Relat Res 473(6):2131–2138

    Article  Google Scholar 

  11. Sershon RA, Courtney PM, Rosenthal BD, Sporer SM, Levine BR (2017) Can demographic variables accurately predict component sizing in primary total knee arthroplasty? J Arthroplasty 32(10):3004–3008

    Article  Google Scholar 

  12. Sershon RA, Li J, Calkins TE, Courtney PM, Nam D, Gerlinger TL, Sporer SM, Levine BR (2019) Prospective validation of a demographically based primary total knee arthroplasty size calculator. J Arthroplasty 34(7):1369–1373

    Article  Google Scholar 

  13. Bhowmik-Stoker M, Scholl L, Khlopas A, Sultan AA, Sodhi N, Moskal JT, Mont MA, Teeny SM (2018) Accurately predicting total knee component size without preoperative radiographs. Surg Technol Int 33:337–342

    PubMed  Google Scholar 

  14. Collins GS, Reitsma JB, Altman DG, Moons KG (2015) Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement. BMJ 350:g7594

    Article  Google Scholar 

  15. Luo W, Phung D, Tran T, Gupta S, Rana S, Karmakar C, Shilton A, Yearwood J, Dimitrova N, Ho TB, Venkatesh S, Berk M (2016) Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J Med Internet Res 18(12):323

    Article  Google Scholar 

  16. Kunze KN, Polce EM, Nwachukwu BU, Chahla J, Nho SJ (2021) Development and internal validation of supervised machine learning algorithms for predicting clinically significant functional improvement in a mixed population of primary hip arthroscopy. Arthroscopy 37(5):1488–1497. https://doi.org/10.1016/j.arthro.2021.01.005

    Article  PubMed  Google Scholar 

  17. Kunze KN, Polce EM, Rasio J, Nho SJ (2020) Machine learning algorithms predict clinically significant improvements in satisfaction after hip arthroscopy. Arthroscopy 37(4):1143–1151. https://doi.org/10.1016/j.arthro.2020.11.027

    Article  PubMed  Google Scholar 

  18. Kunze KN, Burnett RA, Lee EK, Rasio JP, Nho SJ (2020) Development of machine learning algorithms to predict being lost to follow-up after hip arthroscopy for femoroacetabular impingement syndrome. Arthrosc Sports Med Rehabil 2(5):e591–e598

    Article  Google Scholar 

  19. Polce EM, Kunze KN, Fu MC, Garrigues GE, Forsythe B, Nicholson GP, Cole BJ, Verma NN (2020) Development of supervised machine learning algorithms for prediction of satisfaction at 2 years following total shoulder arthroplasty. J Shoulder Elbow Surg 30(6):e290–e299. https://doi.org/10.1016/j.jse.2020.09.007

    Article  PubMed  Google Scholar 

  20. Kunze KN, Polce EM, Sadauskas AJ, Levine BR (2020) Development of machine learning algorithms to predict patient dissatisfaction after primary total knee arthroplasty. J Arthroplasty 35(11):3117–3122

    Article  Google Scholar 

  21. Kunze KN, Karhade AV, Sadauskas AJ, Schwab JH, Levine BR (2020) Development of machine learning algorithms to predict clinically meaningful improvement for the patient-reported health state after total hip arthroplasty. J Arthroplasty 35(8):2119–2123

    Article  Google Scholar 

  22. Kunze KN, Karhade AV, Sadauskas AJ, Schwab JH, Levine BR (2020) Development of machine learning algorithms to predict clinically meaningful improvement for the patient-reported health state after total hip arthroplasty. J Arthroplasty 35(8):2119–2123. https://doi.org/10.1016/j.arth.2020.03.019

    Article  PubMed  Google Scholar 

  23. Breiman L (2001) Random forests. Mach Learn 45(1):5–32

    Article  Google Scholar 

  24. Hastie T, Tibshirani R, Friedman J (2009) The elements of statistical learning: data mining, inference, and prediction. Springer

    Book  Google Scholar 

  25. Friedman JH (2002) Stochastic gradient boosting. Comput Stat Data Anal 38(4):367–378

    Article  Google Scholar 

  26. Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29(5):1189–1232

    Article  Google Scholar 

  27. Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1):1–22

    Article  Google Scholar 

  28. Ribeiro MT, Singh S, Guestrin C (2016) "Why Should I Trust You?": explaining the predictions of any classifier. In: Proceedings of the 22nd SIGKDD international conference on knowledge discovery and data mining, pp 1135–1144

  29. Miller AG, Purtill JJ (2012) Accuracy of digital templating in total knee arthroplasty. Am J Orthop (Belle Mead NJ) 41(11):510–512

    Google Scholar 

  30. Levine B, Fabi D, Deirmengian C (2010) Digital templating in primary total hip and knee arthroplasty. Orthopedics 33(11):797

    Article  Google Scholar 

  31. Wongsak S, Kawinwonggowit V, Mulpruck P, Channoom T, Woratanarat P (2009) Accuracy of knee implants sizing predicted by digital images. J Med Assoc Thai 92(Suppl 6):S85-90

    PubMed  Google Scholar 

  32. Jung WH, Seo JG, Kim DH, Balabadra S, Mandot U, Kumar D (2020) Optimal rotational positioning of tibial component in total knee arthroplasty: determined by linker surgical technique using a high definition CT. Arch Orthop Trauma Surg 140(3):401–408

    Article  Google Scholar 

  33. Klasan A, Twiggs JG, Fritsch BA, Miles BP, Heyse TJ, Solomon M, Parker DA (2020) Correlation of tibial component size and rotation with outcomes after total knee arthroplasty. Arch Orthop Trauma Surg 140(11):1819–1824

    Article  Google Scholar 

  34. Zahn RK, Graef F, Conrad JL, Renner L, Perka C, Hommel H (2020) Accuracy of tibial positioning in the frontal plane: a prospective study comparing conventional and innovative techniques in total knee arthroplasty. Arch Orthop Trauma Surg 140(6):793–800

    Article  CAS  Google Scholar 

  35. Marino D, Patel J, Popovich JM Jr, Cochran J (2020) Patient demographics and anthropometric measurements predict tibial and femoral component sizing in total knee arthroplasty. Arthroplast Today 6(4):860–865

    Article  Google Scholar 

  36. Wallace SJ, Murphy MP, Schiffman CJ, Hopkinson WJ, Brown NM (2020) Demographic data is more predictive of component size than digital radiographic templating in total knee arthroplasty. Knee Surg Relat Res 32(1):63

    Article  Google Scholar 

Download references

Funding

No funding was obtained for this study.

Author information

Authors and Affiliations

  1. Department of Orthopaedic Surgery, Hospital for Special Surgery, New York, NY, USA

    Kyle N. Kunze

  2. University of Wisconsin School of Medicine and Public Health, Madison, WI, USA

    Evan M. Polce & Brett R. Levine

  3. Department of Orthopaedic Surgery, Rush University Medical Center, Chicago, IL, USA

    Arpan Patel

  4. Rothman Orthopaedic Institute at Thomas Jefferson University, Philadelphia, PA, USA

    P. Maxwell Courtney

Authors
  1. Kyle N. Kunze
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Evan M. Polce
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Arpan Patel
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. P. Maxwell Courtney
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Brett R. Levine
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kyle N. Kunze.

Ethics declarations

Conflict of interest

KNK, AP, EMP: no conflicts of interest. PMC: is a paid consultant for Depuy, Hip Innovation Technology, Zimmer; has stock or stock options in Parvizi Surgical Innovation; and is a Board Member or has a Committee Appointment at AAHKS. BRL: is a paid consultant for Link Orthopaedics, Merete, Exactech; receives research support from Zimmer, Artelon; receives royalties, financial or material support from Human Kinetics, Elsevier and SLACK Inc.; and is a Board Member or has a Committee Appointment at AAHKS, MAOA and the AAOS.

Ethical approval

This study was exempt from ethical approval.

Informed consent

Not applicable.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kunze, K.N., Polce, E.M., Patel, A. et al. Validation and performance of a machine-learning derived prediction guide for total knee arthroplasty component sizing. Arch Orthop Trauma Surg 141, 2235–2244 (2021). https://doi.org/10.1007/s00402-021-04041-5

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00402-021-04041-5

Keywords

Search

Navigation