Predicting Risk of Cardiac Arrest in Young Asian Americans: Insights from an Artificial Neural Network Analysis of the Nationwide Cohort

Abstract

We used the Artificial Neural Network (ANN) model to identify predictors of Sudden Cardiac Arrest (SCA) in a national cohort of young Asian patients in the United States. The National Inpatient Sample (2019) was used to identify young Asians (18-44-year-old) who were hospitalized with SCA. The neural network's predicted criteria for SCA were selected. After eliminating missing data, young Asians (n = 65,413) were randomly divided into training (n = 45,094) and testing (n = 19347) groups. Training data (70%) was used to calibrate ANN while testing data (30%) was utilized to assess the algorithm's accuracy. To determine ANN's performance in predicting SCA, we compared the frequency of incorrect prediction between training and testing data and measured the area under the Receiver Operating Curve (AUC). The 2019 young Asian cohort had 327,065 admissions (median age 32 years; 84.2% female), with SCA accounting for 0.21%. The exact rate of error in predictions vs. tests was shown by training data (0.2% vs 0.2%). In descending order, the normalized importance of predictors to accurately predict SCA in young adults included prior history of cardiac arrest, sex, age, diabetes, anxiety disorders, prior coronary artery bypass grafting, hypertension, congenital heart disease, income, peripheral vascular disease, and cancer. The AUC was 0.821, indicating an excellent ANN model for SCA prediction. Our ANN models performed excellently in revealing the order of important predictors of SCA in young Asian American patients. These findings could have a considerable impact on clinical practice to develop risk prediction models to improve the survival outcome in high-risk patients.