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-torecognition 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-torecognition 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.

Key Points Question What is the clinical presentation to emergency medical services among persons with coronavirus disease 2019 (COVID-19)? Findings This cohort study of 124 patients with COVID-19 revealed that most patients with COVID-19 presenting to emergency medical services were older and had multiple chronic health conditions. Initial concern, symptoms, and examination findings were heterogeneous and not consistently characterized as febrile respiratory illness. Meaning The findings of this study suggest that the conventional description of febrile respiratory illness may not adequately identify COVID-19 in the prehospital emergency setting.

No abstract

Rigorous assessment of occupational COVID-19 risk and personal protective equipment (PPE) use is not well-described. We evaluated 9-1-1 emergency medical services (EMS) encounters for patients with COVID-19 to assess occupational exposure, programmatic strategies to reduce exposure and PPE use. We conducted a retrospective cohort investigation of laboratory-confirmed patients with COVID-19 in King County, Washington, USA, who received 9-1-1 EMS responses from 14 February 2020 to 26 March 2020. We reviewed dispatch, EMS and public health surveillance records to evaluate the temporal relationship between exposure and programmatic changes to EMS operations designed to identify high-risk patients, protect the workforce and conserve PPE. There were 274 EMS encounters for 220 unique COVID-19 patients involving 700 unique EMS providers with 988 EMS person-encounters. Use of ‘full’ PPE including mask (surgical or N95), eye protection, gown and gloves (MEGG) was 67%. There were 151 person-exposures among 129 individuals, who required 981 quarantine days. Of the 700 EMS providers, 3 (0.4%) tested positive within 14 days of encounter, though these positive tests were not attributed to occupational exposure from inadequate PPE. Programmatic changes were associated with a temporal reduction in exposures. When stratified at the study encounters midpoint, 94% (142/151) of exposures occurred during the first 137 EMS encounters compared with 6% (9/151) during the second 137 EMS encounters (p<0.01). By the investigation’s final week, EMS deployed MEGG PPE in 34% (3579/10 468) of all EMS person-encounters. Less than 0.5% of EMS providers experienced COVID-19 illness within 14 days of occupational encounter. Programmatic strategies were associated with a reduction in exposures, while achieving a measured use of PPE.