文献速递重症综合管理与镇静镇痛

基于MIMIC-IV数据库的可解释机器学习预测重症监护病房危重患者侵袭性真菌感染风险的回顾性队列研究

INTERPRETABLE MACHINE LEARNING FOR PREDICTING RISK OF INVASIVE FUNGAL INFECTION IN CRITICALLY ILL PATIENTS IN THE INTENSIVE CARE UNIT: A RETROSPECTIVE COHORT STUDY BASED ON MIMIC-IV DATABASE.
PubMed 文献 · Shock · 2024-02-20
一句话结论在MIMIC-IV的26346例ICU成人患者中,基于20个风险因素的BL-SMOTE随机森林模型预测侵袭性真菌感染(发生率1.44%)的AUC为0.88(95%CI 0.84-0.91),可辅助临床早期评估。

本研究为基于MIMIC-IV数据库的回顾性队列研究,纳入ICU停留至少48小时的成人患者26346例,其中379例(1.44%)诊断为侵袭性真菌感染。研究采用LASSO回归筛选特征,BL-SMOTE算法平衡数据,构建六种机器学习模型,并用Shapley加法解释算法评估特征重要性。BL-SMOTE随机森林模型预测性能最佳(AUC=0.88,95%CI 0.84-0.91),对模型影响最大的三个临床特征为透析治疗、APSIII评分和肝病。作者认为该模型可为ICU患者IFI的早期评估提供可靠工具。

要点

  • 研究纳入26346例ICU成人患者,IFI发生率为1.44%(379例),模型基于20个风险因素构建。
  • BL-SMOTE随机森林模型预测性能最佳,AUC=0.88(95%CI 0.84-0.91)。
  • Shapley加法解释显示对模型影响最大的三个特征为透析治疗、APSIII评分和肝病。
  • 作者认为该机器学习模型有助于临床医生早期评估ICU患者IFI的发生。
  • 本研究为回顾性队列研究,数据来源于MIMIC-IV数据库。

适用人群与场景

  • MIMIC-IV数据库中ICU停留至少48小时的成人患者。

研究设计与关键结果

  • 研究类型:基于MIMIC-IV数据库的回顾性队列研究;样本量26346例ICU成人患者,其中379例(1.44%)诊断为侵袭性真菌感染。
  • 采用LASSO回归进行特征选择,BL-SMOTE算法平衡数据集,基于20个风险因素构建六种机器学习预测模型。
  • BL-SMOTE随机森林模型预测性能最高,AUC=0.88(95%CI 0.84-0.91)。
  • Shapley加法解释分析显示,BL-SMOTE随机森林模型中影响最大的三个临床特征为透析治疗、APSIII评分和肝病。

证据类型、等级与局限

  • 证据类型:回顾性队列研究(基于MIMIC-IV数据库)。
  • 作者结论:基于20个风险因素的BL-SMOTE随机森林模型预测性能优越,可辅助临床医生早期评估ICU患者IFI的发生。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,基于20个临床特征的BL-SMOTE随机森林模型对ICU患者IFI具有良好预测价值。
  • 作者认为,该模型可辅助临床医生早期评估ICU患者IFI的发生。

提炼说明

  • 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「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

The delayed diagnosis of invasive fungal infection (IFI) is highly correlated with poor prognosis in patients. Early identification of high-risk patients with invasive fungal infections and timely implementation of targeted measures is beneficial for patients. The objective of this study was to develop a machine learning-based predictive model for invasive fungal infection in patients during their intensive care unit (ICU) stay. Retrospective data was extracted from adult patients in the MIMIC-IV database who spent a minimum of 48 h in the ICU. Feature selection was performed using LASSO regression, and the dataset was balanced using the BL-SMOTE approach. Predictive models were built using six machine learning algorithms. The Shapley additive explanation algorithm was used to assess the impact of various clinical features in the optimal model, enhancing interpretability. The study included 26,346 ICU patients, of whom 379 (1.44%) were diagnosed with invasive fungal infection. The predictive model was developed using 20 risk factors, and the dataset was balanced using the borderline-SMOTE (BL-SMOTE) algorithm. The BL-SMOTE random forest model demonstrated the highest predictive performance (area under curve = 0.88, 95% CI = 0.84-0.91). Shapley additive explanation analysis revealed that the three most influential clinical features in the BL-SMOTE random forest model were dialysis treatment, APSIII scores, and liver disease. The machine learning model provides a reliable tool for predicting the occurrence of IFI in ICU patients. The BL-SMOTE random forest model, based on 20 risk factors, exhibited superior predictive performance and can assist clinicians in early assessment of IFI occurrence in ICU patients. Importance: Invasive fungal infections are characterized by high incidence and high mortality rates characteristics. In this study, we developed a clinical prediction model for invasive fungal infections in critically ill patients based on machine learning algorithms. The results show that the machine learning model based on 20 clinical features has good predictive value.

来源:Shock,查看原文。版权归原作者所有。

参考来源

  1. Cao Y, Li Y, Wang M, et al. INTERPRETABLE MACHINE LEARNING FOR PREDICTING RISK OF INVASIVE FUNGAL INFECTION IN CRITICALLY ILL PATIENTS IN THE INTENSIVE CARE UNIT: A RETROSPECTIVE COHORT STUDY BASED ON MIMIC-IV DATABASE. Shock. 2024. PMID: 38407989. doi:10.1097/SHK.0000000000002312

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。