Danish Drowning Formula for identification of out-of-hospital cardiac arrest from drowning.

BACKGROUND: Accurate, reliable, and sufficient data is required to reduce the burden of drowning by targeting preventive measures and improving treatment. Today's drowning statistics are informed by various methods sometimes based on data sources with questionable reliability. These methods are likely responsible for a systematic and significant underreporting of drowning. This study's aim was to assess the 30-day survival of patients with out-of-hospital cardiac arrest (OHCA) identified in the Danish Cardiac Arrest Registry (DCAR) after applying the Danish Drowning Formula. METHODS: This nationwide, cohort, registry-based study with 30-day follow-up used the Danish Drowning Formula to identify drowning-related OHCA with a resuscitation attempt from the DCAR from January 1st, 2016, through December 31st, 2021. The Danish Drowning Formula is a text-search algorithm constructed for this study based on trigger-words identified from the prehospital medical records of validated drowning cases. The primary outcome was 30-day survival from OHCA. Data were analyzed using multiple logistic regression. RESULTS: Drowning-related OHCA occurred in 374 (1%) patients registered in the DCAR compared to 29,882 patients with OHCA from other causes. Drowning-related OHCA more frequently occurred at a public location (87% vs 25%, p < 0.001) and were more frequently witnessed by bystanders (80% vs 55%, p < 0.001). Both 30-day and 1-year survival for patients with drowning-related OHCA were significantly higher compared to OHCA from other causes (33% vs 14% and 32% vs 13%, respectively, p < 0.001). The adjusted odds ratio for 30-day survival for drowning-related OHCA and other causes of OHCA was 2.3 [1.7-3.2], p < 0.001. Increased 30-day survival was observed for drowning-related OHCA occurring at swimming pools compared to public location OHCA from other causes with an OR of 11.6 [6.0-22.6], p < 0.001. CONCLUSIONS: This study found higher 30-day survival among drowning-related OHCA compared to OHCA from other causes. This study proposed that a text-search algorithm (Danish Drowning Formula) could explore unstructured text fields to identify drowning persons. This method may present a low-resource solution to inform the drowning statistics in the future. REGISTRATION: This study was registered at ClinicalTrials.gov before analyses (NCT05323097).

When the machine is wrong. Characteristics of true and false predictions of Out-of-Hospital Cardiac arrests in emergency calls using a machine-learning model.

BACKGROUND: A machine-learning model trained to recognize emergency calls regarding Out-of-Hospital Cardiac Arrest (OHCA) was tested in clinical practice at Copenhagen Emergency Medical Services (EMS) from September 2018 to December 2019. We aimed to investigate emergency call characteristics where the machine-learning model failed to recognize OHCA or misinterpreted a call as being OHCA. METHODS: All emergency calls were linked to the dispatch database and verified OHCAs were identified by linkage to the Danish Cardiac Arrest Registry. Calls with either false negative or false positive predictions of OHCA were evaluated by trained auditors. Descriptive analyses were performed with absolute numbers and percentages reported. RESULTS: The machine-learning model processed 169,236 calls to Copenhagen EMS and suspected 5,811 (3.4%) of the calls as OHCA, resulting in 84.5% sensitivity and 97.1% specificity. Among OHCAs not recognised by machine-learning model, a condition completely different from OHCA was presented by caller in 31% of the cases. In 28% of unrecognised calls, patient was reported breathing normally, and language barriers were identified in 23% of the cases. Among falsely suspected OHCA, the patient was reported unconscious in 28% of the cases, and in 13% of the false positive cases the machine-learning model interpreted calls regarding dead patients with irreversible signs of death as OHCA. CONCLUSION: Continuous optimization of the language model is needed to improve the prediction of OHCA and thereby improve sensitivity and specificity of the machine-learning model on recognising OHCA in emergency telephone calls.

Pediatric out-of-hospital cardiac arrest in Denmark.

BACKGROUND: Pediatric out-of-hospital cardiac arrest (POHCA) has received limited attention. All causes of POHCA and outcomes were examined during a 4-year period in a Danish nationwide register and prehospital medical records. The aim was to describe the incidence, reversible causes, and survival rates for POHCA in Denmark. METHODS: This is a registry-based follow-up cohort study. All POHCA for a 4-year period (2016-2019) in Denmark were included. All prehospital medical records for the included subjects were reviewed manually by five independent raters establishing whether a presumed reversible cause could be assigned. RESULTS: We identified 173 cases within the study period. The median incidence of POHCA in the population below 17 years of age was 4.2 per 100,000 persons at risk. We found a presumed reversible cause in 48.6% of cases, with hypoxia being the predominant cause of POHCA (42.2%). The thirty-day survival was 40%. Variations were seen across age groups, with the lowest survival rate in cases below 1 year of age. Defibrillators were used more frequently among survivors, with 16% of survivors defibrillated bystanders as opposed to 1.9% in non-survivors and 24% by EMS personnel as opposed to 7.8% in non-survivors. The differences in initial rhythm being shockable was 34% for survivors and 16% for non-survivors. CONCLUSION: We found pediatric out-of-hospital cardiac arrests was a rare event, with higher incidence and mortality in infants compared to other age groups of children. Use of defibrillators was disproportionally higher among survivors. Hypoxia was the most common presumed cause among all age groups.