Abstract
Background
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.
Methods
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.
Results
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.
Conclusion
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.
Keywords
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 accessOne-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:
Subscribe to The Journal of ArthroplastyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Patient satisfaction after total knee arthroplasty.Knee Surg Relat Res. 2016; 28: 1-15
- Patient satisfaction after total knee arthroplasty: who is satisfied and who is not?.Clin Orthop Relat Res. 2010; 468: 57-63
- Machine learning and primary total knee arthroplasty: patient forecasting for a patient-specific payment model.J Arthroplasty. 2018; 33: 3617-3623
- 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)
- 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)
- Internal validation of a predictive model for satisfaction after primary total knee arthroplasty.J Arthroplasty. 2019; 34: 663-670
- 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
- Multiple imputation in the presence of non-normal data.Stat Med. 2017; 36: 606-617
- Random forests.Machine Learn. 2001; 45: 5-32
- The elements of statistical learning: data mining, inference, and prediction.Springer, 2009 ([accessed 10.03.2020])
- Stochastic gradient boosting.Comput Stat Data Anal. 2002; 38: 367-378
- Regularization paths for generalized linear models via coordinate descent.J Stat Softw. 2010; 33: 1-22
- A simple and effective model-based variable importance measure: Cornell University.https://arxiv.org/abs/1805.04755([accessed 04.03.2020])Date: 2019
- Towards better clinical prediction models: seven steps for development and an ABCD for validation.Eur Heart J. 2014; 35: 1925-1931
- Assessing the performance of prediction models: a framework for traditional and novel measures.Epidemiology. 2010; 21: 128-138
- The index of prediction accuracy: an intuitive measure useful for evaluating risk prediction models.Diagn Progn Res. 2018; 2
- Verification of forecasts expressed in terms of probability.Mon weather Rev. 1950; 78: 1-3
- Verification of weather forecasts.in: Malone T.F. Compendium of meteorology. American Meteorological Society, Boston, MA1951: 841-848
- Decision curve analysis: a novel method for evaluating prediction models.Med Decis Making. 2006; 26: 565-574
- 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
- Model-agnostic interpretability of machine learning.: Cornell University.https://arxiv.org/abs/1606.05386([accessed 04.03.2020])Date: 2019
- Patient dissatisfaction following total knee arthroplasty: a systematic review of the literature.J Arthroplasty. 2017; 32: 3854-3860
- Revisiting patient satisfaction following total knee arthroplasty: a longitudinal observational study.BMC Musculoskelet Disord. 2018; 19: 423
- Patient-reported allergies predict worse outcomes after hip and knee arthroplasty: results from a prospective cohort study.J Arthroplasty. 2016; 31: 2746-2749
- Patient reported allergies are a risk factor for poor outcomes in total hip and knee arthroplasty.J Arthroplasty. 2014; 29: 147-149
- Development of machine learning algorithms to predict clinically meaningful improvement for the patient-reported health state after total hip arthroplasty.J Arthroplasty. 2020;
- Machine learning algorithms for prediction of health-related quality-of-life after surgery for mild degenerative cervical myelopathy.Spine J. 2020;
- Development of a machine learning algorithm for prediction of failure of nonoperative management in spinal epidural abscess.Spine J. 2019; 19: 1657-1665
- Development of machine learning algorithms for prediction of mortality in spinal epidural abscess.Spine J. 2019; 19: 1950-1959
Article info
Publication history
Published online: June 01, 2020
Accepted:
May 26,
2020
Received in revised form:
May 21,
2020
Received:
March 23,
2020
Footnotes
One or more of the authors of this paper have disclosed potential or pertinent conflicts of interest, which may include receipt of payment, either direct or indirect, institutional support, or association with an entity in the biomedical field which may be perceived to have potential conflict of interest with this work. For full disclosure statements refer to https://doi.org/10.1016/j.arth.2020.05.061.
Identification
Copyright
© 2020 Elsevier Inc. All rights reserved.
