This study evaluates the performance of Canonical Correlation Analysis (CCA) for predicting the risk of cardiac arrest in individuals with congenital heart disease through the application of fusional Magnetic Resonance Imaging (fMRI) data. The fMRI data used were collected from a cohort of 58 individuals, of which 26 were selected as the target group, who experienced cardiac arrest at least once in their lifetime. The remaining 32 patients were selected as the control group and did not suffer any cardiac arrest episode. Correlation coefficients were extracted from the fMRI data using CCA to identify correlations between the target and the control groups. Results of this analysis indicated that the correlations between the target and the control groups were significant, providing potential predictive validity to the CCA model with respect to cardiac arrest. Furthermore, the CCA model was found to be reliable in terms of distinguishing between high- and low-risk patients, suggesting its potential use as a clinical tool for personalized cardiac care. In conclusion, this study suggests that CCA has the potential to serve as a reliable tool for personalized cardiac care and for predicting risk of cardiac arrest in individuals with congenital heart disease.