文献速递复苏、休克与脓毒症重症综合管理与镇静镇痛

急诊科应用机器学习进行早期脓毒症预测

Early sepsis prediction in the emergency department using machine learning.
PubMed 文献 · Am J Emerg Med · 2025-09-19
一句话结论在疑似脓毒症急诊患者中,使用常规数据的机器学习模型预测器官损伤和30天死亡的AUROC为0.798和0.808,优于qSOFA和NEWS。

本研究为对1431例因疑似脓毒症就诊于急诊科的前瞻性收集数据的事后分析,提取149项常规临床参数,用10折交叉验证开发机器学习模型预测器官损伤和30天死亡率,并事后验证性能、与qSOFA和NEWS比较。机器学习模型预测器官损伤的AUROC为0.798(95%CI 0.775-0.821),预测30天死亡的AUROC为0.808(95%CI 0.777-0.839),优于qSOFA(AUROC 0.557-0.577)和NEWS(AUROC 0.576-0.610)。血清肌酐、SOFA评分、ISAR-HP评分和临床印象对模型评分贡献最大。作者认为机器学习模型相比传统评分系统与改善的预测性能相关,突显其临床决策支持的潜力。

要点

  • 在1431例疑似脓毒症急诊患者中,机器学习模型预测器官损伤AUROC 0.798(95%CI 0.775-0.821),优于qSOFA(0.557-0.577)和NEWS(0.576-0.610)。
  • 机器学习模型预测30天死亡AUROC 0.808(95%CI 0.777-0.839),同样优于qSOFA和NEWS。
  • 模型使用149项急诊常规采集的临床参数,包括电子健康记录和床旁测量数据。
  • 对模型评分贡献最大的参数为血清肌酐、SOFA评分、ISAR-HP评分和临床印象。
  • 作者认为该模型突显了临床决策支持的潜力,但研究为事后分析。

适用人群与场景

  • 因疑似脓毒症就诊于急诊科的成人患者,共1431例,数据为前瞻性收集。

研究设计与关键结果

  • 研究类型为对前瞻性收集数据的死后分析,样本量1431例,人群为急诊科疑似脓毒症患者。
  • 从电子健康记录和床旁测量中提取149项急诊停留期间常规采集的临床参数。
  • 采用10折交叉验证开发机器学习模型,预测器官损伤和30天死亡率,随后验证性能并与qSOFA和NEWS比较。
  • 机器学习模型预测器官损伤的AUROC为0.798(95%CI 0.775-0.821),qSOFA的AUROC为0.557-0.577,NEWS的AUROC为0.576-0.610。
  • 机器学习模型预测30天死亡的AUROC为0.808(95%CI 0.777-0.839),qSOFA和NEWS的AUROC分别为0.557-0.577和0.576-0.610。
  • 对模型评分贡献最大的参数为血清肌酐、SOFA评分、ISAR-HP评分和临床印象。

证据类型、等级与局限

  • 证据类型:对前瞻性收集数据的死后分析。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为,使用急诊常规数据的机器学习模型相比传统评分系统与改善的器官损伤和30天死亡预测性能相关,突显其临床决策支持的潜力。

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

INTRODUCTION: Early recognition of sepsis is critical for timely intervention. Early intervention (eg. with antibiotics) can reduce the risk on organ injury and eventually death. Commonly used clinical scores, such as qSOFA and NEWS, have limited predictive performance to predict organ failure and mortality in patients with early sepsis. Moreover, they require to be estimated by a human operator and lack the capacity to use diverse input sources. Machine learning (ML) models may improve risk stratification by integrating a broader range of parameters.

METHODS: This study is a post-hoc analysis of prospectively collected data from 1431 patients presenting to the ED with suspected sepsis. A total of 149 clinical parameters, which were routinely collected as part of clinical care during ED stay, were extracted from electronic health records and bedside measurements. Machine learning (ML) models were developed in 10-fold cross validation to predict organ injury and 30-day mortality. Model performance was validated afterwards and compared to qSOFA and NEWS.

RESULTS: The ML models achieved an AUROC (area under the receiver operator curve) of 0.798, 95 % CI [0.775, 0.821] for organ injury and 00.808, 95 % CI [0.777, 0.839] for 30-day mortality, outperforming qSOFA (AUROC 0.557-0.577) and NEWS (AUROC 0.576-0.610). Serum creatinine, SOFA score, ISAR-HP score, and clinical impression contributed to most to the model's score.

CONCLUSION: Machine learning models using routinely available ED data were associated with improved predictive performance of organ injury and 30-day mortality in early sepsis compared to conventional scoring systems, highlighting their potential for clinical decision support.

来源:Am J Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. van Wijk RJ, Belur Nagaraj S, Ter Maaten JC, et al. Early sepsis prediction in the emergency department using machine learning. Am J Emerg Med. 2025. PMID: 41027321. doi:10.1016/j.ajem.2025.09.034

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。