多分类机器学习算法在预测初次全膝关节置换术后当日出院中的效用
该研究基于2017至2023年167859例初次全膝关节置换术数据,开发多分类机器学习模型预测当日出院、1至3日出院及延长住院。随机森林表现最佳,平均精确率90.2%、召回率90.3%,多分类准确率90.3%、Cohen kappa 0.85、微平均AUC 0.97。作者认为模型可辅助门诊手术患者选择。
要点
- 随机森林预测住院时长分组表现最佳,平均精确率90.2%、召回率90.3%。
- 随机森林多分类准确率90.3%、Cohen kappa 0.85、微平均AUC 0.97。
- 当日出院、1至3日出院、延长住院率分别为2.1%、88.1%、9.8%。
核心结论
- 机器学习模型能准确识别初次全膝关节置换术后适合当日出院及延长住院风险的患者。
- 作者认为模型可能辅助外科医生选择门诊手术患者,从而改善结局、资源配置和成本效率。
研究设计与样本
- 研究查询数据库识别2017至2023年间167859例初次全膝关节置换术。
- 住院时长分为当日出院(0天)、1至3日出院和延长住院(超过3天)。
- 开发并评估人工神经网络、随机森林、k近邻和XGBoost等机器学习模型,使用混淆矩阵、Cohen kappa和受试者工作特征曲线下面积评价。
主要发现
- 当日出院、1至3日出院和延长住院率分别为2.1%、88.1%和9.8%。
- 随机森林在预测不同住院时长分组中表现最佳,平均精确率90.2%,召回率90.3%。
- 随机森林多分类准确率90.3%,Cohen kappa 0.85,微平均受试者工作特征曲线下面积0.97。
- 住院时长的重要预测因素包括麻醉类型、性别、体重指数、美国麻醉医师协会评分、高血压、年龄和手术时间。
临床怎么用
- 作者认为机器学习模型可能辅助外科医生选择适合门诊手术的患者,从而改善结局、资源配置和成本效率。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Length of stay (LOS) is a substantial driver of costs following primary total knee arthroplasty (TKA), leading to increased efforts targeting same-day discharge (SDD). However, patient selection for SDD TKA remains a challenge, with 7 to 49% of patients failing to achieve planned SDD with current stratification tools. This study aimed to develop and assess multiclass machine learning (ML) models for patient selection for SDD TKA as well as risk for prolonged LOS using a large national patient cohort. METHODS: The database was queried to identify 167,859 primary TKAs between 2017 and 2023. The LOS was categorized into SDD (LOS = zero days), discharge within one to three days, and prolonged LOS (> three days). Machine learning models, including artificial neural networks, random forests (RF), k-nearest neighbors, and XGBoost, were developed and evaluated using the confusion matrix, Cohen's kappa, and the area under the receiver operating characteristic curve. RESULTS: Same-day discharge, discharge within one to three days, and prolonged LOS rates were 2.1, 88.1, and 9.8%, respectively. The RF demonstrated the best performance in predicting different LOS groups with an average precision of 90.2% and a recall of 90.3%. For multiclass classification, RF had an accuracy of 90.3%, a Cohen's kappa of 0.85, and a micro-averaged area under the receiver operating characteristic curve of 0.97. Prominent predictors of LOS included anesthesia type, sex, body mass index, American Society of Anesthesiologists score, hypertension, age, and operation time. CONCLUSIONS: Our findings demonstrate the ability of ML models to accurately identify SDD-eligible and at-risk patients for prolonged LOS after primary TKA. Our models may assist surgeons with patient selection for outpatient surgery, thereby improving outcomes, resource allocation, and cost efficiency of TKA.
引用
- Chen SF, Buddhiraju A, Chen TL, et al. Utility of Multiclass Machine Learning Algorithms in Predicting Same-Day Discharge Following Primary Total Knee Arthroplasty. J Arthroplasty. 2025. PMID: 40912339. doi:10.1016/j.arth.2025.08.072
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。