机器学习预测ICU患者家属的创伤后应激障碍
该研究在2374名ICU患者家属中,于ICU出院90天后使用事件影响量表(IES)及修订版(IES-R)评估PTSD,采用多种监督机器学习方法预测PTSD,并在独立留出测试集上评估。非线性集成树方法(随机森林AUC=0.73 [0.68-0.77]、XGBoost AUC=0.73 [0.69-0.78])预测性能优于正则化线性模型、核模型或深度学习模型。在最佳算法中,对PTSD预测概率正向贡献最大的特征均为不可改变因素:患者年龄较低、ICU停留时间较长、家属为女性、家属年龄较低、家属为配偶/子女、患者在ICU死亡。对丧亲家属的敏感性分析未改变算法的预测性能。作者提出一种基于机器学习的方法在个体水平预测ICU患者家属的PTSD。
要点
- 在2374名ICU患者家属中,随机森林预测ICU出院90天后PTSD的AUC=0.73(0.68-0.77),XGBoost AUC=0.73(0.69-0.78)。
- 非线性集成树方法预测性能优于正则化线性模型、核模型或深度学习模型。
- 对PTSD预测概率正向贡献最大的特征均为不可改变因素:患者年龄较低、ICU停留时间较长、家属为女性、家属年龄较低、家属为配偶/子女、患者在ICU死亡。
- 对丧亲家属的敏感性分析未改变算法的预测性能。
- 作者提出基于机器学习的方法可在个体水平预测ICU患者家属的PTSD。
适用人群与场景
- ICU患者家属,共2374名,于ICU出院90天后评估PTSD。
诊断标准与关键阈值
- 采用事件影响量表(Impact of Event Scale)及事件影响量表修订版(Impact of Event Scale-Revised)在ICU出院90天后测量PTSD。
研究设计与关键结果
- 研究采用多种监督机器学习方法预测家属PTSD,并在独立留出测试数据集上评估。
- 随机森林预测PTSD的AUC=0.73(0.68-0.77),XGBoost的AUC=0.73(0.69-0.78),非线性集成树方法性能优于正则化线性模型、核模型或深度学习模型。
- 在最佳算法中,对PTSD预测概率正向贡献最大的特征均为不可改变因素:患者年龄较低、ICU停留时间较长、家属为女性、家属年龄较低、家属为配偶/子女、患者在ICU死亡。
- 对丧亲家属的敏感性分析未改变算法的预测性能。
证据类型、等级与局限
- 证据类型:机器学习预测模型研究,样本量2374名家属,在独立留出测试数据集上评估。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者提出一种基于机器学习的方法,可在个体水平预测ICU患者家属的PTSD。
- 在该模型中,PTSD主要受不可改变因素影响。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
PURPOSE: Post-traumatic stress disorder (PTSD) can affect family members of patients admitted to the intensive care unit (ICU). Easily accessible patient's and relative's information may help develop accurate risk stratification tools to direct relatives at higher risk of PTSD toward appropriate management.
METHODS: PTSD was measured 90 days after ICU discharge using validated instruments (Impact of Event Scale and Impact of Event Scale-Revised) in 2374 family members. Various supervised machine learning approaches were used to predict PTSD in family members and evaluated on an independent held-out test dataset. To better understand variables' contributions to PTSD predicted probability, we used machine learning interpretability methods on the best predictive algorithm.
RESULTS: Non-linear ensemble learning tree-based methods showed better predictive performances (Random Forest-area under curve, AUC = 0.73 [0.68-0.77] and XGBoost-AUC = 0.73 [0.69-0.78]) than regularized linear models, kernel-based models, or deep learning models. In the best performing algorithm, most important features that positively contributed to PTSD's predicted probability were all non-modifiable factors, namely, lower patient's age, longer duration of ICU stay, relative's female sex, lower relative's age, relative being a spouse/child, and patient's death in ICU. A sensitivity analysis in bereaved relatives did not alter the algorithm's predictive performance.
CONCLUSION: We propose a machine learning-based approach to predict PTSD in relatives of ICU patients at an individual level. In this model, PTSD is mostly influenced by non-modifiable factors.
参考来源
- Dupont T, Kentish-Barnes N, Pochard F, et al. Prediction of post-traumatic stress disorder in family members of ICU patients: a machine learning approach. Intensive Care Med. 2023. PMID: 38112774. doi:10.1007/s00134-023-07288-1
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。