Machine learning as a supportive tool to recognize cardiac arrest in emergency calls

RESUSCITATION

卷:138

Article

Blomberg, Stig Nikolaj^1,2  Folke, Fredrik^1,2,3  Ersboll, Annette Kjaer⁴  Christensen, Helle Collatz¹  Torp-Pedersen, Christian^5,6  Sayre, Michael R.⁷  Counts, Catherine R.⁷  Lippert, Freddy K.^1,2 

[1] Emergency Med Serv Copenhagen, Telegrafvej 5, DK-2750 Copenhagen, Denmark

[2] Univ Copenhagen, Dept Clin Med, Telegrafvej 5, DK-2750 Copenhagen, Denmark

[3] Gentofte Univ Hosp, Dept Cardiol, Hellerup, Denmark

[4] Univ Southern Denmark, Natl Inst Publ Hlth, Odense, Denmark

[5] Aalborg Univ Hosp, Dept Clin Epidemiol, Aalborg, Denmark

[6] Aalborg Univ, Dept Hlth Sci & Technol, Aalborg, Denmark

[7] Univ Washington, Dept Emergency Med, Seattle, WA 98195 USA

关键词: Artificial intelligence;    Machine learning;    Cardiopulmonary resuscitation;    Emergency medical services;    Out-of-hospital cardiac arrest;    Detection time;    Dispatch-assisted cardiopulmonary resuscitation;   

DOI  :  10.1016/j.resuscitation.2019.01.015

来源: Elsevier

【 摘 要 】

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.

【 授权许可】

Free