RESUMEN

BACKGROUND: The COVID-19 pandemic has posed significant challenges to healthcare systems worldwide, including an increase in out-of-hospital cardiac arrests (OHCA). Healthcare providers are now required to use personal protective equipment (PPE) during cardiopulmonary resuscitation (CPR). Additionally, mechanical CPR devices have been introduced to reduce the number of personnel required for resuscitation. This study aimed to compare the outcomes of CPR performed with a mechanical device and the outcomes of manual CPR performed by personnel wearing PPE. METHODS: This multicenter observational study utilized data from the Korean Cardiac Arrest Research Consortium registry. The study population consisted of OHCA patients who underwent CPR in emergency departments (EDs) between March 2020 and June 2021. Patients were divided into two equal propensity score matched groups: mechanical CPR group (n = 421) and PPE-equipped manual CPR group (n = 421). Primary outcomes included survival rates and favorable neurological outcomes at discharge. Total CPR duration in the ED was also assessed. RESULTS: There were no significant between-group differences with respect to survival rate at discharge (mechanical CPR: 7.4% vs PPE-equipped manual CPR: 8.3%) or favorable neurological outcomes (3.3% vs. 3.8%, respectively). However, the mechanical CPR group had a longer duration of CPR in the ED compared to the manual CPR group. CONCLUSION: This study found no significant differences in survival rates and neurological outcomes between mechanical CPR and PPE-equipped manual CPR in the ED setting. However, a longer total CPR duration was observed in the mechanical CPR group. Further research is required to explore the impact of PPE on healthcare providers' performance and fatigue during CPR in the context of the pandemic and beyond.

Asunto(s)

RESUMEN

This study evaluated automated machine learning (AutoML) in classifying the presence or absence of hemoperitoneum in ultrasonography (USG) images of Morrison's pouch. In this multicenter, retrospective study, 864 trauma patients from trauma and emergency medical centers in South Korea were included. In all, 2200 USG images (1100 hemoperitoneum and 1100 normal) were collected. Of these, 1800 images were used for training and 200 were used for the internal validation of AutoML. External validation was performed using 100 hemoperitoneum images and 100 normal images collected separately from a trauma center that were not included in the training and internal validation sets. Google's open-source AutoML was used to train the algorithm in classifying hemoperitoneum in USG images, followed by internal and external validation. In the internal validation, the sensitivity, specificity, and area under the receiver operating characteristic (AUROC) curve were 95%, 99%, and 0.97, respectively. In the external validation, the sensitivity, specificity, and AUROC were 94%, 99%, and 0.97, respectively. The performances of AutoML in the internal and external validation were not statistically different (p = 0.78). A publicly available, general-purpose AutoML can accurately classify the presence or absence of hemoperitoneum in USG images of the Morrison's pouch of real-world trauma patients.