文献速递复苏、休克与脓毒症重症综合管理与镇静镇痛

机器学习模型用于脓毒症高危患者早期识别的开发与评估

Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis.
PubMed 文献 · Ann Emerg Med · 2019-01-17
一句话结论在49家社区医院急诊的回顾性数据中,机器学习RoS评分对脓毒症筛查的判别力优于SOFA、qSOFA等基准工具,但尚需独立机构验证。

研究利用49家城市社区医院急诊22个月共2,759,529例成人患者的回顾性电子健康记录数据,以Rhee临床监测标准定义脓毒症,通过三阶段特征选择(回顾现有模型、咨询本地专家、梯度提升监督学习)开发RoS评分。RoS在所有时间阈值上判别力最高(AUC 0.93–0.97),1小时和24小时敏感性分别为67.7%和84.6%,均优于SOFA(49.2%和80.4%);精确率分别为27.6%和28.8%,也高于SOFA(12.2%和11.4%)。qSOFA敏感性较低(1小时3.7%,24小时23.5%)。作者结论认为RoS较基准工具更及时且判别力更强,但需独立机构验证。

要点

  • 在49家社区医院急诊成人患者中,RoS评分所有时间阈值AUC为0.93–0.97,判别力高于SOFA、qSOFA、SIRS、MEWS和NEWS。
  • 1小时敏感性RoS 67.7% vs SOFA 49.2%,24小时RoS 84.6% vs SOFA 80.4%,RoS均更高。
  • 1小时精确率RoS 27.6% vs SOFA 12.2%,24小时RoS 28.8% vs SOFA 11.4%,RoS均更高。
  • qSOFA敏感性相对较低:1小时3.7%,24小时23.5%。
  • 作者结论:RoS较基准筛查工具更及时、判别力更强,但需在独立机构验证RoS评分。

适用人群与场景

  • 来自49家城市社区医院急诊科、在22个月期间就诊的成人患者,共2,759,529例,使用其回顾性电子健康记录数据。

诊断标准与关键阈值

  • 以Rhee临床监测标准作为脓毒症的标准定义,并作为开发模型的主要目标。

研究设计与关键结果

  • 研究类型为回顾性电子健康记录数据分析,数据来自49家城市社区医院急诊科22个月期间共2,759,529例成人患者,数据随机分为训练队列和测试队列以推导并评估模型。
  • 特征选择分3个阶段:第一,回顾现有脓毒症筛查模型;第二,咨询本地主题专家;第三,使用名为梯度提升的监督机器学习方法。
  • RoS评分在所有时间阈值上均为判别力最高的筛查工具,AUC为0.93–0.97。
  • 与判别力次高的基准工具SOFA相比,RoS敏感性更高:1小时67.7% vs 49.2%,24小时84.6% vs 80.4%。
  • 与SOFA相比,RoS精确率更高:1小时27.6% vs 12.2%,24小时28.8% vs 11.4%。
  • qSOFA敏感性相对较低:1小时3.7%,24小时23.5%。
  • 性能评估时间点为索引时间后1、3、6、12和24小时。

证据类型、等级与局限

  • 证据类型:回顾性研究,使用电子健康记录数据开发并评估机器学习模型。
  • 局限:作者指出需进一步研究以在独立机构验证RoS评分。

对床旁实践的改变

  • 作者结论认为,在此回顾性研究中,RoS较基准筛查工具(包括Sepsis-3工作组推荐的qSOFA)更及时且判别力更强。
  • 作者指出需进一步研究以在独立机构验证RoS评分。

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

STUDY OBJECTIVE: The Third International Consensus Definitions (Sepsis-3) Task Force recommended the use of the quick Sequential [Sepsis-related] Organ Failure Assessment (qSOFA) score to screen patients for sepsis outside of the ICU. However, subsequent studies raise concerns about the sensitivity of qSOFA as a screening tool. We aim to use machine learning to develop a new sepsis screening tool, the Risk of Sepsis (RoS) score, and compare it with a slate of benchmark sepsis-screening tools, including the Systemic Inflammatory Response Syndrome, Sequential Organ Failure Assessment (SOFA), qSOFA, Modified Early Warning Score, and National Early Warning Score.

METHODS: We used retrospective electronic health record data from adult patients who presented to 49 urban community hospital emergency departments during a 22-month period (N=2,759,529). We used the Rhee clinical surveillance criteria as our standard definition of sepsis and as the primary target for developing our model. The data were randomly split into training and test cohorts to derive and then evaluate the model. A feature selection process was carried out in 3 stages: first, we reviewed existing models for sepsis screening; second, we consulted with local subject matter experts; and third, we used a supervised machine learning called gradient boosting. Key metrics of performance included alert rate, area under the receiver operating characteristic curve, sensitivity, specificity, and precision. Performance was assessed at 1, 3, 6, 12, and 24 hours after an index time.

RESULTS: The RoS score was the most discriminant screening tool at all time thresholds (area under the receiver operating characteristic curve 0.93 to 0.97). Compared with the next most discriminant benchmark (Sequential Organ Failure Assessment), RoS was significantly more sensitive (67.7% versus 49.2% at 1 hour and 84.6% versus 80.4% at 24 hours) and precise (27.6% versus 12.2% at 1 hour and 28.8% versus 11.4% at 24 hours). The sensitivity of qSOFA was relatively low (3.7% at 1 hour and 23.5% at 24 hours).

CONCLUSION: In this retrospective study, RoS was more timely and discriminant than benchmark screening tools, including those recommend by the Sepsis-3 Task Force. Further study is needed to validate the RoS score at independent sites.

来源:Ann Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Delahanty RJ, Alvarez J, Flynn LM, et al. Development and Evaluation of a Machine Learning Model for the Early Identification of Patients at Risk for Sepsis. Ann Emerg Med. 2019. PMID: 30661855. doi:10.1016/j.annemergmed.2018.11.036

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。