文献速递儿科与产科急症重症综合管理与镇静镇痛

儿科急诊分诊中实施的危重指数

Criticality index conducted in pediatric emergency department triage.
PubMed 文献 · Am J Emerg Med · 2021-05-06
一句话结论基于分诊信息的机器学习模型可准确预测儿科急诊患者去向,高危重与中危重AUROC分别为0.982和0.968。

本研究回顾性分析2013至2020年一家儿科四级医疗中心585,142次急诊就诊数据,训练极端梯度提升机器学习模型,将患者分为高危重(入住ICU 4小时内、入院4小时内死亡或急诊死亡)、中危重(需住院但无需ICU)和低危重(离院回家)三类。模型使用分诊生命体征、分诊护理评估、人口学资料及既往6个月病史(诊断、用药、医疗利用)。测试集(40%)中,高危重和中危重的一对多AUROC分别为0.982(95%CI 0.980, 0.983)和0.968(0.967, 0.969),多分类宏平均AUROC为0.976,AUPRC为0.754。结论认为仅用分诊时可得信息即可准确预测儿科急诊去向,为改善医疗质量和患者结局提供机会。

要点

  • 高危重定义:入院4小时内需ICU、入院4小时内死亡或急诊死亡;中危重:需住院但无需ICU;低危重:离院回家。
  • 高危重与中危重的一对多AUROC分别为0.982(95%CI 0.980, 0.983)和0.968(0.967, 0.969)。
  • 多分类宏平均AUROC为0.976,AUPRC为0.754。
  • 对模型性能最重要的特征包括静脉用药史、毛细血管再充盈、急诊严重指数级别、住院史、使用补充供氧装置、年龄和ICU入住史。
  • 模型仅使用分诊时可得信息及既往6个月病史,未使用后续检查结果。

适用人群与场景

  • 2013至2020年一家儿科四级医疗中心的585,142次急诊就诊,数据回顾性分析。
  • 模型训练使用随机选取的50%数据,测试使用预留的40%数据。

诊断标准与关键阈值

  • 高危重:入院4小时内需ICU、入院4小时内死亡或急诊死亡。
  • 中危重:需住院但无需ICU。
  • 低危重:离院回家。

研究设计与关键结果

  • 研究类型:回顾性分析;样本量:585,142次急诊就诊;单中心(一家儿科四级医疗中心);时间:2013至2020年。
  • 干预:极端梯度提升机器学习模型,使用分诊生命体征、分诊护理评估、人口学资料及既往6个月病史(诊断、用药、医疗利用)预测去向。
  • 危重分布:高危重1.5%,中危重7.1%,低危重91.4%。
  • 主要终点:高危重一对多AUROC 0.982(95%CI 0.980, 0.983);中危重一对多AUROC 0.968(95%CI 0.967, 0.969)。
  • 多分类宏平均AUROC 0.976,AUPRC 0.754。
  • 对模型性能最重要的特征:静脉用药史、毛细血管再充盈、急诊严重指数级别、住院史、使用补充供氧装置、年龄、ICU入住史。

证据类型、等级与局限

  • 证据类型:回顾性队列研究(基于电子健康记录)。
  • 局限:原文未报告局限性

对床旁实践的改变

  • 作者认为,儿科急诊去向可基于分诊时可得信息准确预测,为改善医疗质量和患者结局提供机会。

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

OBJECTIVE: To develop and analyze the performance of a machine learning model capable of predicting the disposition of patients presenting to a pediatric emergency department (ED) based on triage assessment and historical information mined from electronic health records.

METHODS: We retrospectively reviewed data from 585,142 ED visits at a pediatric quaternary care institution between 2013 and 2020. An extreme gradient boosting machine learning model was trained on a randomly selected training data set (50%) to stratify patients into 3 classes: (1) high criticality (patients requiring intensive care unit [ICU] care within 4 h of hospital admission, patients who died within 4 h of admission, and patients who died in the ED); (2) moderate criticality (patients requiring hospitalization without the need for ICU care); and (3) low criticality (patients discharged home). Variables considered during model development included triage vital signs, aspects of triage nursing assessment, demographics, and historical information (diagnoses, medication use, and healthcare utilization). Historical factors were limited to the 6 months preceding the index ED visit. The model was tested on a previously withheld test data set (40%), and its performance analyzed.

RESULTS: The distribution of criticality among high, moderate, and low was 1.5%, 7.1%, and 91.4%, respectively. The one-versus-all area under the receiver operating characteristic (AUROC) curve for high and moderate criticality was 0.982 (95% CI 0.980, 0.983) and 0.968 (0.967, 0.969). The multi-class macro average AUROC and area under the receiver operating characteristic curve were 0.976 and 0.754. The features most integral to model performance included history of intravenous medications, capillary refill, emergency severity index level, history of hospitalization, use of a supplemental oxygen device, age, and history of admission to the ICU.

CONCLUSION: Pediatric ED disposition can be accurately predicted using information available at triage, providing an opportunity to improve quality of care and patient outcomes.

来源:Am J Emerg Med,查看原文。版权归原作者所有。

参考来源

  1. Heyming TW, Knudsen-Robbins C, Feaster W, et al. Criticality index conducted in pediatric emergency department triage. Am J Emerg Med. 2021. PMID: 33975133. doi:10.1016/j.ajem.2021.05.004

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。