Evaluation of optimal scene time interval for out-of-hospital cardiac arrest using a deep neural network

Abstract

AIM: This study aims to develop a cardiac arrest prediction model using deep learning (CAPD) algorithm and to validate the developed algorithm by evaluating the change in out-of-hospital cardiac arrest patient prognosis according to the increase in scene time interval (STI). METHODS: We conducted a retrospective cohort study using smart advanced life support trial data collected by the National Emergency Center from January 2016 to December 2019. The smart advanced life support data were randomly partitioned into derivation and validation datasets. The performance of the CAPD model using the patient's age, sex, event witness, bystander cardiopulmonary resuscitation (CPR), administration of epinephrine, initial shockable rhythm, prehospital defibrillation, provision of advanced life support, response time interval, and STI as prediction variables for prediction of a patient's prognosis was compared with conventional machine learning methods. After fixing other values of the input data, the changes in prognosis of the patient with respect to the increase in STI was observed. RESULTS: A total of 16,992 patients were included in this study. The area under the receiver operating characteristic curve values for predicting prehospital return of spontaneous circulation (ROSC) and favorable neurological outcomes were 0.828 (95% confidence interval 0.826-0.830) and 0.907 (0.914-0.910), respectively. Our algorithm significantly outperformed other artificial intelligence algorithms and conventional methods. The neurological recovery rate was predicted to decrease to 1/3 of that at the beginning of cardiopulmonary resuscitation when the STI was 28 min, and the prehospital ROSC was predicted to decrease to 1/2 of its initial level when the STI was 30 min. CONCLUSION: The CAPD exhibits potential and effectiveness in identifying patients with ROSC and favorable neurological outcomes for prehospital resuscitation.