文献速递重症综合管理与镇静镇痛复苏、休克与脓毒症

基于图卷积网络的电子健康记录噪声数据插补

Graph Convolutional Networks-Based Noisy Data Imputation in Electronic Health Record.
PubMed 文献 · Crit Care Med · 2020-01-01
一句话结论基于图卷积网络的脓毒症早期预警系统可在脓毒症发作前6小时进行预测,在Physionet Challenge 2019官方阶段效用评分为-0.101,ROC曲线下面积0.782。

本研究基于电子病历数据,提出一种深度学习早期预警系统,用于在脓毒症发作前进行预测。研究采用回顾性队列,纳入来自三家独立医院的超过60,000例ICU患者,每例患者每小时40个临床变量(生命体征、实验室结果),脓毒症发作依据Sepsis-3定义。算法在Physionet Challenge 2019评分函数下评估,可预测脓毒症发作前4、6、8或12小时,官方阶段效用评分-0.101,ROC曲线下面积0.782,精确率-召回率曲线下面积0.041,准确率0.786,F值0.046。作者认为该方法可作为一种实用的早期预警系统用于真实医院环境。

要点

  • 研究纳入三家独立医院的超过60,000例ICU患者,每例患者每小时40个临床变量(生命体征、实验室结果),脓毒症发作依据Sepsis-3定义。
  • 所提算法可在脓毒症发作前4、6、8或12小时进行预测,官方阶段效用评分为-0.101。
  • 官方阶段ROC曲线下面积0.782,精确率-召回率曲线下面积0.041,准确率0.786,F值0.046。
  • 所提方法在ROC曲线下面积、精确率-召回率曲线下面积和评分方面均取得更优结果,并能更早预测更多脓毒症患者。
  • 作者认为该方法可作为一种实用的早期预警系统用于真实医院环境。

适用人群与场景

  • 来自三家独立医院的超过60,000例ICU患者,每例患者每小时40个临床变量(生命体征、实验室结果)。

诊断标准与关键阈值

  • 脓毒症发作依据Sepsis-3定义。

研究设计与关键结果

  • 研究为回顾性队列,纳入三家独立医院的超过60,000例ICU患者,每例患者每小时40个临床变量(生命体征、实验室结果),脓毒症发作依据Sepsis-3定义。
  • 所提算法可在脓毒症发作前4、6、8或12小时进行预测,并比较了在短时间内能预测多少脓毒症患者与其他方法的差异。
  • 官方阶段所提方法效用评分为-0.101,ROC曲线下面积0.782,精确率-召回率曲线下面积0.041,准确率0.786,F值0.046。
  • 所提方法在ROC曲线下面积、精确率-召回率曲线下面积和评分方面均取得更优结果,并能更早预测更多脓毒症患者。

证据类型、等级与局限

  • 证据类型:回顾性队列研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,基于Physionet Challenge 2019,所提方法可准确且早期地预测脓毒症发作,可作为一种实用的早期预警系统用于真实医院环境。

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

OBJECTIVES: A deep learning-based early warning system is proposed to predict sepsis prior to its onset.

DESIGN: A novel algorithm was devised to detect sepsis 6 hours prior to its onset based on electronic medical records.

SETTING: Retrospective cohorts from three separate hospitals are used in this study. Sepsis onset was defined based on Sepsis-3. Algorithms are evaluated based on the score function used in the Physionet Challenge 2019.

PATIENTS: Over 60,000 ICU patients with 40 clinical variables (vital signs, laboratory results) for each hour of a patient's ICU stay were used.

INTERVENTIONS: None.

MEASUREMENTS AND MAIN RESULTS: The proposed algorithm predicted the onset of sepsis in the preceding n hours (where n = 4, 6, 8, or 12). Furthermore, the proposed method compared how many sepsis patients can be predicted in a short time with other methods. To interpret a given result in a clinical perspective, the relationship between input variables and the probability of the proposed method were presented. The proposed method achieved superior results (area under the receiver operating characteristic curve, area under the precision-recall curve, and score) and predicted more sepsis patients in advance. In official phase, the proposed method showed the utility score of -0.101, area under the receiver operating characteristic curve 0.782, area under the precision-recall curve 0.041, accuracy 0.786, and F-measure 0.046.

CONCLUSIONS: Using Physionet Challenge 2019, the proposed method can accurately and early predict the onset of sepsis. The proposed method can be a practical early warning system in the environment of real hospitals.

来源:Crit Care Med,查看原文。版权归原作者所有。

参考来源

  1. Lee BT, Kwon OY, Park H, et al. Graph Convolutional Networks-Based Noisy Data Imputation in Electronic Health Record. Crit Care Med. 2020. PMID: 32947466. doi:10.1097/CCM.0000000000004583

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。