«上一篇/Previous Article|本期目录/Table of Contents|下一篇/Next Article»

中华老年骨科与康复电子杂志[ISSN:1674-3911/CN:11-9292/R]

卷:

期数:

2025年06期

页码:

337-344

栏目:

膝关节

出版日期:

2025-12-05

文章信息/Info

Title:

Comparison of predictive performance of multiple models of factors affecting chronic pain after total knee arthroplasty

作者:

荣锦1 骆明星2 王禹2 刘婷婷2 张宏斌2

063000 唐山市第二医院手术室1，创伤骨科2

Author(s):

Rong Jin1;  Luo Mingxing2;  Wang Yu2;  Liu Tingting2;  Zhang Hongbin2

1Department of Operating Room, 2Department of Traumatic Orthopedics, The Second Hospital of Tangshan City, Tangshan 063000, China

关键词:

机器学习;  全膝关节置换;  慢性疼痛;  影响因素

Keywords:

Machine learning;  Total knee replacement;  Chronic pain;  Influencing factor

DOI:

10.3877/cma.j.issn.2096-0263.2025.06.003

文献标志码:

A

摘要:

目的 探讨关于全膝关节置换术（TKA）后患者发生慢性疼痛的影响因素，比较不同机器学习模型的预测性能。方法 回顾性选取2021年10月至2024年5月于本院接受TKA治疗的膝骨性关节炎患者278例，根据留出法按7:3的比例随机将其分为训练集（195例）和测试集（83例）。术前采用疼痛数字评定量表（NRS）评估患者术前、出院时疼痛情况；采用焦虑抑郁量表（HADS）评估患者情绪状况。训练集通过采用5折交叉验证法获取最优超参数，构建逻辑回归（LR）、随机森林（RF）、极端梯度提升（XGBoost）、支持向量机（SVM）模型；验证集用于内部验证。以精确率、灵敏度、特异度、召回率、F1值和曲线下面积（AUC）等评估模型的预测性能，对比出性能最优的模型，使用Shapley加性解释（SHAP）算法评估重要风险变量，分析各临床特征对模型的影响。结果 278例接受TKA治疗的膝骨性关节炎患者中发生术后慢性疼痛的有87例（31.29%）。与无疼痛组相比，训练集中疼痛组患者合并糖尿病、术后发生下肢静脉血栓占比、术前HADS评分、术前NRS评分、术后CRP水平均显著较高（P＜0.05），两组在年龄、性别、身体质量指数（BMI）、合并高血压、冠心病、病程、ASA分级、术前膝关节压痛、手术部位、手术时间、住院时间、出院时NRS评分方面比较无明显差异（P＞0.05）；经对比发现，LR、RF、SVM、XGBoost模型的AUC分别为0.725、0.945、0.780、0.884，均大于0.7，其中RF模型的AUC和精确率均最大，提示RF模型的预测性能优于其他三种模型；在最优模型中利用SHAP算法发现，术后CRP、术前HADS、术前NRS评分、术后下肢静脉血栓、合并糖尿病为患者TKA术后慢性疼痛的重要影响因素。结论 基于机器学习算法构建的TKA术后慢性疼痛的预测模型均显示出良好的预测性能，其中RF模型综合预测效能最优，其风险因素对于临床防治慢性疼痛具有重要指导意义。

Abstract:

Objective To explore the machine learning model of chronic pain after total knee arthroplasty (TKA) and analyze its influencing factors. Methods 278 patients with knee osteoarthritis who received TKA in our hospital from October 2021 to May 2024 were selected and randomly divided into training set (195 cases) and test set (83 cases) according to the ratio of 7:3. The pain Numerical Rating Scale (NRS) was used to evaluate the pain before surgery and at discharge. The anxiety and depression Scale (HADS) was used to evaluate the emotional status of the patients. The optimal hyperparameters of the training set were obtained by using the 5-fold cross-validation method, and logistic regression (LR), random forest (RF), extreme gradient Lift (XGBoost) and support vector machine (SVM) models were constructed. Validation sets are used for internal validation. Accuracy, sensitivity, specificity, recall rate, F1 value and area under the curve (AUC) were used to evaluate the predictive performance of the models, and the models with the best performance were compared. Shapley additive interpretation (SHAP) algorithm was used to evaluate important risk variables, and the influence of clinical characteristics on the models was analyzed. Results Among 278 patients with knee osteoarthritis treated with TKA, 87 case had chronic pain after surgery (31.29%). Compared with the pain-free group, the patients in the training intensive pain group with diabetes mellitus, the proportion of postoperative thrombosis in lower extremity vein, preoperative HADS score, preoperative NRS score and postoperative CRP level were significantly higher (P<0.05). There were no significant differences between the two groups in terms of age, gender, body mass index (BMI), comorbidities of hypertension, coronary heart disease, disease duration, ASA grading, preoperative knee joint tenderness, surgical site, surgical time, length of hospital stay, and NRS score at discharge (P>0.05). The comparison showed that the AUC of LR, RF, SVM and XGBoost models were 0.725, 0.945, 0.780 and 0.884, respectively, all greater than 0.7, and the AUC and accuracy of RF model were the largest, suggesting that the prediction performance of RF model was better than the other three models. In the optimal model, SHAP algorithm was used to find that postoperative CRP, preoperative HADS, preoperative NRS score, postoperative venous thrombosis of lower extremity, and diabetes mellitus were important factors affecting chronic pain after TKA. Conclusion All prediction models of chronic pain after TKA based on machine learning algorithm show good prediction performance, among which RF model has the best comprehensive prediction efficiency, and its risk factors have important guiding significance for clinical prevention and treatment of chronic pain.

备注/Memo

备注/Memo:

基金项目：河北省医学科学研究重点课题计划项目（20201451）

常用功能

更新日期/Last Update: 2026-05-18