Interethnic validation of artificial intelligence for prediction of atrial fibrillation using sinus rhythm electrocardiogram

Aims We aimed to develop and comprehensively evaluate our artificial intelligence model for predicting atrial fibrillation based on standard 12-lead sinus rhythm electrocardiogram (ECG) images in a Korean population, and to validate its performance in Brazilian patient cohorts. Methods We developed a modified convolutional neural network (CNN) model using a dataset comprising 811 542 ECGs from 121 600 patients at Seoul National University Bundang Hospital (2003–2020). Ninety percent of the patients were allocated to the training dataset, while the remaining 10% were assigned to the internal validation dataset. External validation was performed using the CODE 15% dataset, an open ECG dataset from the Telehealth Network of Minas Gerais, Brazil, by applying a 1 : 4 (atrial fibrillation : non-atrial fibrillation) random sampling strategy. Results In the internal validation, our artificial intelligence model achieved an area under the receiver-operating characteristic curve (AUROC) of 0.907 [95% confidence interval (CI): 0.897–0.916] for atrial fibrillation prediction. In the external interethnic validation with the CODE 15% dataset, the artificial intelligence model exhibited an AUROC of 0.884 (95% CI: 0.869–0.900), which increased to 0.906 (95% CI: 0.893–0.919) when adjusted for age and sex. In the subset of patients with ‘normal ECG’ interpretations, the AUROC was 0.826 (95% CI: 0.769–0.883), increasing to 0.861 (95% CI: 0.814–0.908) after applying the same adjustments. Conclusion Our artificial intelligence-powered sinus rhythm ECG interpretation model demonstrated excellent performance in predicting paroxysmal or incident atrial fibrillation, with valid performance in the Brazilian population as well. This suggests that the model has the potential for broad application across different ethnic groups.