Abstract:

Objective To develop an early atrial fibrillation (AF) risk prediction model based on large-scale electrocardiogram (ECG) data from the Chinese population. Methods The data of multiple ECG records of 30 383 patients admitted in the Chinese PLA General Hospital between 2009 and 2023 were randomly divided into the training set and the internal testing set in a 7:3 ratio. The predictive factors were selected based on the training set using univariate analysis, LASSO regression, and the Boruta algorithm. Cox proportional hazards regression was used to establish the ECG model and the composite model incorporating age, gender, and ECG model score. The discrimination power, calibration, and clinical net benefits of the models were evaluated using the area under the receiver operating characteristic curve (AUROC), calibration curves, and decision curves. Results The cohort included 51.1% male patients with a median age of the patients of 51 (36, 62) years and an AF incidence of 4.5% (1370/30 383). In the ECG model, the parameters related to the P wave and QRS complex were identified as significant predictors. In the testing set, the AUROC of the ECG model for predicting 5-year AF risk was 0.77 (95% CI: 0.74-0.80), which was increased to 0.81 (95% CI: 0.78-0.83) after incorporating age and gender, with a net reclassification improvement of 0.123 and an integrated discrimination improvement of 0.04 (P<0.05). The calibration curve of the model was close to the diagonal line. Decision curve analysis showed that the clinical net benefit of the composite model was higher than that of the ECG model across the majority of threshold probability. Conclusion The composite model incorporating quantitative ECG features during sinus rhythm, along with age and gender, can effectively predict AF risk in the Chinese population, thus providing a low-cost screening tool for early AF risk assessment and management.

Key words: electrocardiogram, atrial fibrillation, LASSO regression, Boruta algorithm