文献速递关节外科

基于全国性队列的机器学习模型识别初次全髋关节置换术后延长住院时间的高风险患者

Machine Learning Models Based on a National-Scale Cohort Identify Patients at High Risk for Prolonged Lengths of Stay Following Primary Total Hip Arthroplasty.
PubMed 文献 · J Arthroplasty · 2023-06-12

本研究基于246265例初次全髋关节置换术(THA)数据,以住院时间(LOS)超过队列第75百分位定义为延长LOS,构建人工神经网络、随机森林、直方图梯度提升和k近邻四种机器学习模型。所有模型区分度优异(AUC 0.72-0.74)且校准良好,人工神经网络表现最佳(AUC 0.73)。年龄、实验室检查和手术变量是延长LOS的最强预测因子。

要点

  • 基于246265例THA数据构建的四种机器学习模型预测延长LOS(超过第75百分位)表现优异,AUC为0.72-0.74。
  • 人工神经网络表现最佳,AUC 0.73,校准斜率0.99,校准截距-0.01,Brier分数0.185。
  • 年龄、实验室检查和手术变量是延长LOS的最强预测因子。

核心结论

  • 机器学习模型的优异预测性能表明其能够识别易发生延长LOS的患者。
  • 许多导致延长LOS的因素可被优化以缩短高风险患者的住院时间。

研究设计与样本

  • 研究分析了来自大型数据库的246265例THA,采用递归特征消除筛选候选预测因子,构建人工神经网络、随机森林、直方图梯度提升和k近邻四种机器学习模型,并通过区分度、校准度和效用评估模型性能。

主要发现

  • 所有模型在训练和测试中区分度优异(AUC=0.72至0.74),校准良好(斜率0.83至1.18,截距-0.01至0.11,Brier分数0.185至0.192)。
  • 人工神经网络表现最佳,AUC为0.73,校准斜率为0.99,校准截距为-0.01,Brier分数为0.185。
  • 所有模型在决策曲线分析中产生的净收益高于默认治疗策略。
  • 年龄、实验室检查和手术变量是延长LOS的最强预测因子。

关键数值与推荐

  • 延长LOS定义为超过队列中所有LOS的第75百分位。

临床怎么用

  • 原文未据此给出推荐。

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: Existing machine learning models that predicted prolonged lengths of stay (LOS) following primary total hip arthroplasty (THA) were limited by the small training volume and exclusion of important patient factors. This study aimed to develop machine learning models using a national-scale data set and examine their performance in predicting prolonged LOS following THA. METHODS: A total of 246,265 THAs were analyzed from a large database. Prolonged LOS was defined as exceeding the 75th percentile of all LOSs in the cohort. Candidate predictors of prolonged LOS were selected by recursive feature elimination and used to construct four machine learning models-artificial neural network, random forest, histogram-based gradient boosting, and k-nearest neighbor. The model performance was assessed by discrimination, calibration, and utility. RESULTS: All models exhibited excellent performance in discrimination (area under the receiver operating characteristic curve [AUC] = 0.72 to 0.74) and calibration (slope: 0.83 to 1.18, intercept: -0.01 to 0.11, Brier score: 0.185 to 0.192) during both training and testing sessions. The artificial neural network was the best performer with an AUC of 0.73, calibration slope of 0.99, calibration intercept of -0.01, and Brier score of 0.185. All models showed great utility by producing higher net benefits than the default treatment strategies in the decision curve analyses. Age, laboratory tests, and surgical variables were the strongest predictors of prolonged LOS. CONCLUSION: The excellent prediction performance of machine learning models demonstrated their capacity to identify patients prone to prolonged LOS. Many factors contributing to prolonged LOS can be optimized to minimize hospital stay for high-risk patients.

来源:J Arthroplasty,查看原文。版权归原作者所有。

引用

  1. Chen TL, Buddhiraju A, Costales TG, et al. Machine Learning Models Based on a National-Scale Cohort Identify Patients at High Risk for Prolonged Lengths of Stay Following Primary Total Hip Arthroplasty. J Arthroplasty. 2023. PMID: 37315634. doi:10.1016/j.arth.2023.06.009

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。