Research
Print page Print page
Switch language
The Capital Region of Denmark - a part of Copenhagen University Hospital
E-pub ahead of print

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

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Out-of-Hospital Cardiac Arrest in Patients With Psychiatric Disorders - Characteristics and Outcomes

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Improving the cost-effectiveness of laypersons' paediatric basic life support skills training: A randomised non-inferiority study

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Automated external defibrillator accessibility is crucial for bystander defibrillation and survival: A registry-based study

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. A nationwide investigation of CPR courses, books, and skill retention

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Association between Type D personality and outcomes in patients with non-ischemic heart failure

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Satisfaction of 30 402 callers to a medical helpline of the Emergency Medical Services Copenhagen: a retrospective cohort study

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Polygenic predisposition to breast cancer and the risk of coronary artery disease

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Cardiovascular Manifestations of Systemic Sclerosis: A Danish Nationwide Cohort Study

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Rate and rhythm therapy in patients with atrial fibrillation and the risk of pacing and bradyarrhythmia

    Research output: Contribution to journalJournal articleResearchpeer-review

View graph of relations

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.

Original languageEnglish
JournalResuscitation
ISSN0300-9572
DOIs
Publication statusE-pub ahead of print - 18 Jan 2019

ID: 56557711