Department of Orthopedic Surgery, Seoul National University College of Medicine, Seoul National University Bundang Hospital, South Korea.
Department of Orthopedic Surgery, Seoul National University College of Medicine, Seoul National University Bundang Hospital, South Korea.
Knee. 2023 Oct;44:253-261. doi: 10.1016/j.knee.2023.08.018. Epub 2023 Sep 11.
Patient satisfaction following primary total knee arthroplasty (TKA) is a crucial part to evaluate the success of the procedure. The purpose of this study was to develop to predict patient satisfaction following TKA.
Satisfaction outcome data after 435 consecutive conventional TKAs performed between August 2020 and December 2021 were retrospectively collected. The total 26 input data were collected. The most favorable algorithm was first found using logistic regression (LR) and machine learning (ML) algorithms. To evaluate the predictive performance of the models, both area under curve (AUC) and F1-score were used as the primary metrics. The shapley additive explanations (SHAP) feature explanation in XGBoost and LR analysis were performed to interpret the model.
The performance of extreme gradient boosting classifier (XGBoost) was only higher than that of conventional LR in AUC (0.782 vs. 0.689). Comparing the F-1 score, only XGBoost showed better performance than LR (0.857 vs. 0.800). The most predictive feature in XGBoost was Short Form-36 physical and mental component summary scores (SF-36 MCS), followed by Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC) pain, Bone mineral density (BMD). In the LR analysis, lumbar spine disease, WOMAC pain, and BMD were statistically significant.
XGboost showed the best performance and was superior to conventional LR in the prediction of patient satisfaction after TKA. The SF-36 MCS was the most important feature in the ML model. WOMAC pain and BMD were meaningful variables and demonstrated a linear relationship with satisfaction in both the LR and ML models.
Retrospective cohort study; Level of evidence 3.
初次全膝关节置换术（TKA）后患者满意度是评估手术成功的关键指标。本研究旨在建立 TKA 后患者满意度的预测模型。
回顾性收集了 2020 年 8 月至 2021 年 12 月期间 435 例连续行常规 TKA 患者的满意度随访资料。共采集 26 个输入数据。首先使用逻辑回归（LR）和机器学习（ML）算法寻找最有利的算法。为了评估模型的预测性能，使用曲线下面积（AUC）和 F1 评分作为主要指标。在 XGBoost 和 LR 分析中进行了 SHAP 特征解释，以解释模型。
极端梯度提升分类器（XGBoost）的性能仅在 AUC 方面高于传统 LR（0.782 比 0.689）。比较 F1 评分，只有 XGBoost 优于 LR（0.857 比 0.800）。XGBoost 中最具预测性的特征是 36 项简明健康调查问卷（SF-36 MCS），其次是西部安大略省和麦克马斯特大学骨关节炎指数（WOMAC）疼痛、骨密度（BMD）。在 LR 分析中，腰椎疾病、WOMAC 疼痛和 BMD 具有统计学意义。
XGBoost 在 TKA 后患者满意度预测方面的表现优于传统 LR，其性能最佳。SF-36 MCS 是 ML 模型中最重要的特征。WOMAC 疼痛和 BMD 是有意义的变量，在 LR 和 ML 模型中均与满意度呈线性关系。
回顾性队列研究；证据水平 3。
