Multimodal data integration to predict atrial fibrillation.

Aims: Many studies have utilized data sources such as clinical variables, polygenic risk scores, electrocardiogram (ECG), and plasma proteins to predict the risk of atrial fibrillation (AF). However, few studies have integrated all four sources from a single study to comprehensively assess AF prediction. Methods and results: We included 8374 (Visit 3, 1993-95) and 3730 (Visit 5, 2011-13) participants from the Atherosclerosis Risk in Communities Study to predict incident AF and prevalent (but covert) AF. We constructed a (i) clinical risk score using CHARGE-AF clinical variables, (ii) polygenic risk score using pre-determined weights, (iii) protein risk score using regularized logistic regression, and (iv) ECG risk score from a convolutional neural network. Risk prediction performance was measured using regularized logistic regression. After a median follow-up of 15.1 years, 1910 AF events occurred since Visit 3 and 229 participants had prevalent AF at Visit 5. The area under curve (AUC) improved from 0.660 to 0.752 (95% CI, 0.741-0.763) and from 0.737 to 0.854 (95% CI, 0.828-0.880) after addition of the polygenic risk score to the CHARGE-AF clinical variables for predicting incident and prevalent AF, respectively. Further addition of ECG and protein risk scores improved the AUC to 0.763 (95% CI, 0.753-0.772) and 0.875 (95% CI, 0.851-0.899) for predicting incident and prevalent AF, respectively. Conclusion: A combination of clinical and polygenic risk scores was the most effective and parsimonious approach to predicting AF. Further addition of an ECG risk score or protein risk score provided only modest incremental improvement for predicting AF.