基于机器学习的电子分诊系统在临床结局区分上比急诊严重度指数更准确
该多中心回顾性横断面研究纳入来自城市和社区急诊科的172,726次急诊就诊,评估基于随机森林模型的电子分诊系统(e-triage),该系统利用生命体征、主诉和活动性病史并行预测危重症监护、急诊操作和住院需求,并将风险转化为分诊等级。e-triage预测的曲线下面积为0.73至0.92,在两家急诊科对临床结局的识别能力等同或优于ESI。在匹配ESI患者分布后,e-triage识别出超过10%(14,326例)的ESI 3级患者需要上调分诊,这些患者危重症监护或急诊操作风险(ESI 3级1.7% vs 上调分诊6.2%)和住院风险(18.9% vs 45.4%)均显著增高。作者认为e-triage能更准确地对ESI 3级患者进行分类,并提示可利用预测分析支持分诊决策,但需进一步前瞻性验证。
要点
- e-triage对急诊就诊者临床结局预测的曲线下面积为0.73至0.92,在两家急诊科识别能力等同或优于ESI。
- 在匹配ESI分布后,e-triage识别出14,326例(超过10%)ESI 3级患者需上调分诊,其危重症监护或急诊操作风险为6.2%,而ESI 3级为1.7%。
- 上调分诊的ESI 3级患者住院风险为45.4%,而ESI 3级为18.9%。
- e-triage为超过65%被分诊为ESI 3级的急诊就诊提供了基于风险区分的依据。
- 作者认为e-triage能更准确地对ESI 3级患者进行分类,但需进一步前瞻性验证。
适用人群与场景
- 来自城市和社区急诊科的172,726次急诊就诊,为多中心回顾性横断面研究人群。
研究设计与关键结果
- 研究类型为多中心回顾性横断面研究,纳入来自城市和社区急诊科的172,726次急诊就诊。
- e-triage由应用于分诊数据(生命体征、主诉和活动性病史)的随机森林模型组成,并行预测危重症监护、急诊操作和住院需求,并将风险转化为分诊等级。
- e-triage预测的曲线下面积为0.73至0.92,在两家急诊科对临床结局的识别能力等同或优于ESI。
- 在匹配ESI患者分布后,e-triage识别出超过10%(14,326例)的ESI 3级患者需要上调分诊,其危重症监护或急诊操作风险为6.2%,而ESI 3级为1.7%;住院风险为45.4%,而ESI 3级为18.9%。
- e-triage为超过65%被分诊为ESI 3级的急诊就诊提供了基于风险区分的依据。
证据类型、等级与局限
- 证据类型为多中心回顾性横断面研究。
- 局限:需进一步前瞻性验证。
对床旁实践的改变
- 作者认为e-triage能更准确地对ESI 3级患者进行分类,并提示可利用预测分析支持分诊决策。
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
STUDY OBJECTIVE: Standards for emergency department (ED) triage in the United States rely heavily on subjective assessment and are limited in their ability to risk-stratify patients. This study seeks to evaluate an electronic triage system (e-triage) based on machine learning that predicts likelihood of acute outcomes enabling improved patient differentiation.
METHODS: A multisite, retrospective, cross-sectional study of 172,726 ED visits from urban and community EDs was conducted. E-triage is composed of a random forest model applied to triage data (vital signs, chief complaint, and active medical history) that predicts the need for critical care, an emergency procedure, and inpatient hospitalization in parallel and translates risk to triage level designations. Predicted outcomes and secondary outcomes of elevated troponin and lactate levels were evaluated and compared with the Emergency Severity Index (ESI).
RESULTS: E-triage predictions had an area under the curve ranging from 0.73 to 0.92 and demonstrated equivalent or improved identification of clinical patient outcomes compared with ESI at both EDs. E-triage provided rationale for risk-based differentiation of the more than 65% of ED visits triaged to ESI level 3. Matching the ESI patient distribution for comparisons, e-triage identified more than 10% (14,326 patients) of ESI level 3 patients requiring up triage who had substantially increased risk of critical care or emergency procedure (1.7% ESI level 3 versus 6.2% up triaged) and hospitalization (18.9% versus 45.4%) across EDs.
CONCLUSION: E-triage more accurately classifies ESI level 3 patients and highlights opportunities to use predictive analytics to support triage decisionmaking. Further prospective validation is needed.
参考来源
- Levin S, Toerper M, Hamrock E, et al. Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index. Ann Emerg Med. 2017. PMID: 28888332. doi:10.1016/j.annemergmed.2017.08.005
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。