Stig Nikolaj Blomberg1, Fredrik Folke2, Annette Kjær Ersbøll3, Helle Collatz Christensen4, Christian Torp-Pedersen5, Michael R Sayre6, Catherine R Counts6, Freddy K Lippert7. 1. Emergency Medical Services Copenhagen, Denmark; Department of Clinical Medicine, University of Copenhagen, Denmark. Electronic address: Stig.Nikolaj.Fasmer.Blomberg@regionh.dk. 2. Emergency Medical Services Copenhagen, Denmark; Department of Clinical Medicine, University of Copenhagen, Denmark; Department of Cardiology, Gentofte University Hospital, Denmark. 3. National Institute of Public Health, University of Southern Denmark, Denmark. 4. Emergency Medical Services Copenhagen, Denmark. 5. Department of Clinical Epidemiology, Aalborg University Hospital, Denmark; Department of Health Science and Technology, Aalborg University, Denmark. 6. Department of Emergency Medicine, University of Washington, United States. 7. Emergency Medical Services Copenhagen, Denmark; Department of Clinical Medicine, University of Copenhagen, Denmark.
Abstract
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.
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.
Authors: Kuan-Chen Chin; Yu-Chia Cheng; Wen-Chu Chiang; Albert Y Chen; Jen-Tang Sun; Chih-Yen Ou; Chun-Hua Hu; Ming-Chi Tsai; Matthew Huei-Ming Ma Journal: J Med Internet Res Date: 2022-06-10 Impact factor: 7.076
Authors: Jani Paulin; Akseli Reunamo; Jouni Kurola; Hans Moen; Sanna Salanterä; Heikki Riihimäki; Tero Vesanen; Mari Koivisto; Timo Iirola Journal: BMC Med Inform Decis Mak Date: 2022-06-23 Impact factor: 3.298
Authors: Theresa M Olasveengen; Mary E Mancini; Gavin D Perkins; Suzanne Avis; Steven Brooks; Maaret Castrén; Sung Phil Chung; Julie Considine; Keith Couper; Raffo Escalante; Tetsuo Hatanaka; Kevin K C Hung; Peter Kudenchuk; Swee Han Lim; Chika Nishiyama; Giuseppe Ristagno; Federico Semeraro; Christopher M Smith; Michael A Smyth; Christian Vaillancourt; Jerry P Nolan; Mary Fran Hazinski; Peter T Morley Journal: Resuscitation Date: 2020-10-21 Impact factor: 5.262