文献速递重症综合管理与镇静镇痛消化、代谢与肾脏急症

机器学习预测创伤性脑损伤后严重急性肾损伤

A Machine Learning Approach for the Prediction of Severe Acute Kidney Injury Following Traumatic Brain Injury.
PubMed 文献 · Neurocrit Care · 2022-10-04
一句话结论在MIMIC-IV中808例中重度TBI患者中,随机森林模型外部验证预测严重AKI的AUC为0.819(95%CI 0.783-0.851),校准良好(P=0.795)。

该回顾性队列研究利用MIMIC-IV与eICU-CRD两个公共数据库,开发并验证机器学习模型以预测创伤性脑损伤患者发生严重急性肾损伤(3期及以上)的风险。研究使用递归特征消除筛选入住ICU 24小时内获得的候选预测因子,以AUC和决策曲线分析评价区分能力,以校准曲线评价校准性能。MIMIC-IV中纳入808例中重度TBI(GCS<12)患者,其中60例(7.43%)发生严重AKI;在eICU-CRD外部验证中,随机森林模型AUC最高,为0.819(95%CI 0.783-0.851),校准曲线显示校准良好(P=0.795)。作者认为随机森林模型区分能力优于其他模型,在线计算器可促进其应用,可能改善严重AKI的早期识别及患者临床结局。

要点

  • MIMIC-IV中808例中重度TBI(GCS<12)患者中,60例(7.43%)发生严重AKI(3期及以上)。
  • 外部验证于eICU-CRD,随机森林模型预测严重AKI的AUC最高,为0.819(95%CI 0.783-0.851)。
  • 随机森林模型校准曲线显示校准良好(P=0.795)。
  • 预测因子为入住ICU 24小时内获得的变量,经递归特征消除筛选。
  • 作者认为随机森林模型区分能力优于其他模型,在线计算器可能改善严重AKI早期识别。

适用人群与场景

  • 中重度创伤性脑损伤(msTBI,定义为Glasgow昏迷评分<12)患者,入住ICU。
  • 研究基于MIMIC-IV与eICU-CRD两个公共数据库的回顾性队列。

诊断标准与关键阈值

  • 严重AKI定义为急性肾损伤3期或以上。
  • msTBI定义为Glasgow昏迷评分<12。

研究设计与关键结果

  • 研究类型:回顾性队列研究,使用MIMIC-IV与eICU-CRD两个公共数据库。
  • MIMIC-IV数据库纳入808例中重度TBI(GCS<12)患者,其中60例(7.43%)发生严重AKI。
  • 候选预测因子为入住ICU 24小时内获得的变量,经递归特征消除筛选。
  • 外部验证于eICU-CRD:随机森林模型AUC最高,为0.819(95%CI 0.783-0.851)。
  • 校准曲线:随机森林模型校准良好(P=0.795)。

证据类型、等级与局限

  • 证据类型:回顾性队列研究,使用公共数据库MIMIC-IV和eICU-CRD。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为随机森林模型在预测严重AKI方面区分能力优于其他模型。
  • 作者认为在线计算器可促进该模型的应用,可能改善中重度TBI患者严重AKI的早期识别并改善临床结局。

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

BACKGROUND: Acute kidney injury (AKI), a prevalent non-neurological complication following traumatic brain injury (TBI), is a major clinical issue with an unfavorable prognosis. This study aimed to develop and validate machine learning models to predict severe AKI (stage 3 or greater) incidence in patients with TBI.

METHODS: A retrospective cohort study was conducted by using two public databases: the Medical Information Mart for Intensive Care IV (MIMIC)-IV and the eICU Collaborative Research Database (eICU-CRD). Recursive feature elimination was used to select candidate predictors obtained within 24 h of intensive care unit admission. The area under the curve and decision curve analysis curves were used to determine the discriminatory ability. On the other hand, the calibration curve was employed to evaluate the calibrated performance of the newly developed machine learning models.

RESULTS: In the MIMIC-IV database, there were 808 patients diagnosed with moderate and severe TBI (msTBI) (msTBI is defined as Glasgow Coma Score < 12). Of these, 60 (7.43%) patients experienced severe AKI. External validation in the eICU-CRD indicated that the random forest (RF) model had the highest area under the curve of 0.819 (95% confidence interval 0.783-0.851). Furthermore, in the calibration curve, the RF model was well calibrated (P = 0.795).

CONCLUSIONS: In this study, the RF model demonstrated better discrimination in predicting severe AKI than other models. An online calculator could facilitate its application, potentially improving the early detection of severe AKI and subsequently improving the clinical outcomes among patients with msTBI.

来源:Neurocrit Care,查看原文。版权归原作者所有。

参考来源

  1. Peng C, Yang F, Li L, et al. A Machine Learning Approach for the Prediction of Severe Acute Kidney Injury Following Traumatic Brain Injury. Neurocrit Care. 2022. PMID: 36195818. doi:10.1007/s12028-022-01606-z

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。