文献速递复苏、休克与脓毒症心脑血管急症

机器学习作为辅助工具在急救电话中识别心脏骤停

Machine learning as a supportive tool to recognize cardiac arrest in emergency calls.
PubMed 文献 · Resuscitation · 2019-01-18
一句话结论在急救电话中,机器学习框架识别院外心脏骤停的敏感性(84.1% vs 72.5%)和识别时间(中位44秒 vs 54秒)均优于调度员,但阳性预测值较低(20.9% vs 33.0%)。

该研究基于2014年哥本哈根急救调度中心接听的108,607次急救电话,其中918次(0.8%)为可分析的院外心脏骤停电话。研究训练机器学习框架从录音中识别心脏骤停,并与调度员的实际识别情况比较。结果显示机器学习敏感性更高(84.1% vs 72.5%,p<0.001)、特异性更低(97.3% vs 98.8%,p<0.001)、阳性预测值更低(20.9% vs 33.0%,p<0.001),识别时间更短(中位44秒 vs 54秒,p<0.001)。作者认为机器学习可能作为调度员的决策支持工具。

要点

  • 在108,607次急救电话中,918次(0.8%)为可分析的院外心脏骤停电话。
  • 机器学习框架识别心脏骤停的敏感性为84.1%,高于调度员的72.5%(p<0.001)。
  • 机器学习框架的特异性为97.3%,低于调度员的98.8%(p<0.001);阳性预测值为20.9%,低于调度员的33.0%(p<0.001)。
  • 机器学习框架识别心脏骤停的中位时间为44秒,短于调度员的54秒(p<0.001)。
  • 作者认为机器学习可能作为急救调度员的决策支持工具发挥重要作用。

适用人群与场景

  • 2014年由哥本哈根急救调度中心接听并响应的所有急救电话相关事件。
  • 分析对象为其中可分析的院外心脏骤停电话录音。

研究设计与关键结果

  • 研究类型为基于急救电话录音的机器学习框架开发与验证研究,共分析108,607次急救电话,其中918次(0.8%)为可分析的院外心脏骤停电话。
  • 与调度员相比,机器学习框架识别院外心脏骤停的敏感性更高(84.1% vs 72.5%,p<0.001),特异性更低(97.3% vs 98.8%,p<0.001),阳性预测值更低(20.9% vs 33.0%,p<0.001)。
  • 机器学习框架识别心脏骤停的中位时间显著短于调度员(44秒 vs 54秒,p<0.001)。

证据类型、等级与局限

  • 证据类型:基于急救电话录音的机器学习框架开发与验证研究。
  • 局限:原文未报告局限性。

对床旁实践的改变

  • 作者认为机器学习可能作为急救调度员的决策支持工具发挥重要作用。

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

BACKGROUND: Emergency medical dispatchers fail to identify approximately 25% of cases of out of hospital cardiac arrest, thus lose the opportunity to provide the caller instructions in cardiopulmonary resuscitation. We examined whether a machine learning framework could recognize out-of-hospital cardiac arrest from audio files of calls to the emergency medical dispatch center.

METHODS: For all incidents responded to by Emergency Medical Dispatch Center Copenhagen in 2014, the associated call was retrieved. A machine learning framework was trained to recognize cardiac arrest from the recorded calls. Sensitivity, specificity, and positive predictive value for recognizing out-of-hospital cardiac arrest were calculated. The performance of the machine learning framework was compared to the actual recognition and time-to-recognition of cardiac arrest by medical dispatchers.

RESULTS: We examined 108,607 emergency calls, of which 918 (0.8%) were out-of-hospital cardiac arrest calls eligible for analysis. Compared with medical dispatchers, the machine learning framework had a significantly higher sensitivity (72.5% vs. 84.1%, p < 0.001) with lower specificity (98.8% vs. 97.3%, p < 0.001). The machine learning framework had a lower positive predictive value than dispatchers (20.9% vs. 33.0%, p < 0.001). Time-to-recognition was significantly shorter for the machine learning framework compared to the dispatchers (median 44 seconds vs. 54 s, p < 0.001).

CONCLUSIONS: A machine learning framework performed better than emergency medical dispatchers for identifying out-of-hospital cardiac arrest in emergency phone calls. Machine learning may play an important role as a decision support tool for emergency medical dispatchers.

来源:Resuscitation,查看原文。版权归原作者所有。

参考来源

  1. Blomberg SN, Folke F, Ersbøll AK, et al. Machine learning as a supportive tool to recognize cardiac arrest in emergency calls. Resuscitation. 2019. PMID: 30664917. doi:10.1016/j.resuscitation.2019.01.015

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。