Machine learning methods are comparable to logistic regression techniques in predicting severe walking limitation following total knee arthroplasty

• Published in: Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA Vol. 28; no. 10; pp. 3207 - 3216
• Main Authors: Pua, Yong-Hao, Kang, Hakmook, Thumboo, Julian, Clark, Ross Allan, Chew, Eleanor Shu-Xian, Poon, Cheryl Lian-Li, Chong, Hwei-Chi, Yeo, Seng-Jin
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2020; Springer Nature B.V
• Subjects: Aged; Algorithms; Arthroplasty (knee); Arthroplasty, Replacement, Knee - adverse effects; Calibration; Female; Humans; Joint replacement surgery; Knee; Learning algorithms; Logistic Models; Machine Learning; Male; Medicine; Medicine & Public Health; Middle Aged; Mobility Limitation; Orthopedics; Postoperative Complications - physiopathology; Prognosis; Registries; Regression analysis; Regression models; Spline functions; Statistical analysis; Treatment Outcome; Walking; Knee; Algorithms; Prediction; Machine learning; Replacement; Arthroplasty; Artificial intelligence
• ISSN: 0942-2056; 1433-7347
• DOI: 10.1007/s00167-019-05822-7

Purpose Machine-learning methods are flexible prediction algorithms with potential advantages over conventional regression. This study aimed to use machine learning methods to predict post-total knee arthroplasty (TKA) walking limitation, and to compare their performance with that of logistic regression. Methods From the department’s clinical registry, a cohort of 4026 patients who underwent elective, primary TKA between July 2013 and July 2017 was identified. Candidate predictors included demographics and preoperative clinical, psychosocial, and outcome measures. The primary outcome was severe walking limitation at 6 months post-TKA, defined as a maximum walk time ≤ 15 min. Eight common regression (logistic, penalized logistic, and ordinal logistic with natural splines) and ensemble machine learning (random forest, extreme gradient boosting, and SuperLearner) methods were implemented to predict the probability of severe walking limitation. Models were compared on discrimination and calibration metrics. Results At 6 months post-TKA, 13% of patients had severe walking limitation. Machine learning and logistic regression models performed moderately [mean area under the ROC curves (AUC) 0.73–0.75]. Overall, the ordinal logistic regression model performed best while the SuperLearner performed best among machine learning methods, with negligible differences between them (Brier score difference, < 0.001; 95% CI [− 0.0025, 0.002]). Conclusions When predicting post-TKA physical function, several machine learning methods did not outperform logistic regression—in particular, ordinal logistic regression that does not assume linearity in its predictors. Level of evidence Prognostic level II