文献速递复苏、休克与脓毒症心脑血管急症

人工智能预测心肺复苏中可电击心律:院内场景

Artificial intelligence for predicting shockable rhythm during cardiopulmonary resuscitation: In-hospital setting.
PubMed 文献 · Resuscitation · 2024-07-17
一句话结论基于按压伪影心电图的AI模型可预测可电击心律,AUROC为0.8672,手工按压0.8771、机械按压0.8466。

本研究为回顾性观察研究,使用前瞻性收集的数据库,纳入2021年9月至2024年2月在急诊科发生或到达急诊科时心脏骤停的成年患者,分析每次心律检查前5秒按压伪影心电图,基于卷积神经网络构建AI模型,并按患者划分训练、验证和测试集。共使用172例患者的1,889份按压伪影心电图,预测可电击心律的AUROC为0.8672(95%CI 0.8161-0.9122),手工按压和机械按压的AUROC分别为0.8771(95%CI 0.8054-0.9408)和0.8466(95%CI 0.7630-0.9138)。作者认为该模型可减少心肺复苏中断并可能改善结局。

要点

  • 在急诊科心脏骤停患者中,利用按压伪影心电图预测可电击心律的AI模型AUROC为0.8672(95%CI 0.8161-0.9122)。
  • 按按压方式分层,手工按压AUROC为0.8771(95%CI 0.8054-0.9408),机械按压AUROC为0.8466(95%CI 0.7630-0.9138)。
  • 研究使用每次心律检查前5秒的按压伪影心电图,共1,889份来自172例患者,按患者划分数据集以避免同一患者跨集。
  • 采用梯度加权类激活映射展示AI可解释性,作者认为该模型可减少心肺复苏中断并可能改善结局。

适用人群与场景

  • 2021年9月至2024年2月期间到达急诊科时心脏骤停或在急诊科内发生心脏骤停的成年患者。

研究设计与关键结果

  • 回顾性观察研究,使用前瞻性收集的数据库,纳入172例患者共1,889份按压伪影心电图,基于卷积神经网络构建AI模型,按患者划分训练、验证和测试集。
  • 预测可电击心律的AUROC为0.8672(95%CI 0.8161-0.9122)。
  • 手工按压的AUROC为0.8771(95%CI 0.8054-0.9408),机械按压的AUROC为0.8466(95%CI 0.7630-0.9138)。

证据类型、等级与局限

  • 证据类型:回顾性观察研究,使用前瞻性收集的数据库。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为该模型可减少心肺复苏中断并可能改善结局。

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

AIM OF THE STUDY: This study aimed to develop an artificial intelligence (AI) model capable of predicting shockable rhythms from electrocardiograms (ECGs) with compression artifacts using real-world data from emergency department (ED) settings. Additionally, we aimed to explore the black box nature of AI models, providing explainability.

METHODS: This study is retrospective, observational study using a prospectively collected database. Adult patients who presented to the ED with cardiac arrest or experienced cardiac arrest in the ED between September 2021 and February 2024 were included. ECGs with a compression artifact of 5 s before every rhythm check were used for analysis. The AI model was designed based on convolutional neural networks. The ECG data were assigned into training, validation, and testing sets on a per-patient basis to ensure that ECGs from the same patient did not appear in multiple sets. Gradient-weighted class activation mapping was employed to demonstrate AI explainability.

RESULTS: A total of 1,889 ECGs with compression artifacts from 172 patients were used. The area under the receiver operating characteristic curve (AUROC) for shockable rhythm prediction was 0.8672 (95% confidence interval [CI]: 0.8161-0.9122). The AUROCs for manual and mechanical compression were 0.8771 (95% CI: 0.8054-0.9408) and 0.8466 (95% CI: 0.7630-0.9138), respectively.

CONCLUSION: This study was the first to accurately predict shockable rhythms during compression using an AI model trained with actual patient ECGs recorded during resuscitation. Furthermore, we demonstrated the explainability of the AI. This model can minimize interruption of cardiopulmonary resuscitation and potentially lead to improved outcomes.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Ahn S, Jung S, Park JH, et al. Artificial intelligence for predicting shockable rhythm during cardiopulmonary resuscitation: In-hospital setting. Resuscitation. 2024. PMID: 39029581. doi:10.1016/j.resuscitation.2024.110325

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。