Background
Graves’ disease (GD) is known to be associated with atrial fibrillation (AF). Artificial intelligence (AI)-enabled ECGs using a convolutional neural network can identify the signature of silent AF. Whether the existing AI model is able to identify patients at highest risk of GD-related AF is unknown.
Methods
Patients with GD (2009-2019) at our institution were included. GD-associated AF was defined as AF diagnosed ≤30 days before or any time after GD. Probability of AF was obtained from the AI platform on ECGs in sinus rhythm done within 2 months before and up to 2 years after GD; when multiple ECGs were present, the earliest was considered. ECGs done at/after AF diagnosis were excluded. Risk factors were analyzed using cox proportional hazards. For multivariate analysis, all variables with p <0.2 at univariate analysis were entered into the model and a stepwise selection method was used to generate the final model.
Results
430 patients with GD were included; mean age 50±17, 78% female. AF was diagnosed in 43 (10%) patients with a median (IQR) of 11 (0-863) days after GD. ECGs used were obtained 27 (4-690) days before AF. Univariate risk factors included older age [HR 1.07 (1.04-1.09) p <.001], male gender [HR 1.9 (1.01-3.6) p =.047], hypertension (HR 4.4 (2.2-8.8), p<.001), hyperlipidemia [HR 2.8 (1.5-5.1), p = .001], history of coronary artery disease [HR 5.0 (2.4-10.5), p <.001], chronic kidney disease [HR 2.9 (1.4-6.3), p =.006], and probability of AF >5% [HR 5.9 (3.2-10.9). p<.001]. At multivariate analysis, risk factors for AF were AI ECG probability of AF>5% [HR 4.2 (2.1-8.1), p<.001], older age [HR 1.05 (1.03-1.07) per year, p=<.001] and overt hyperthyroidism (free T4>1.7) [HR 3.4 (1.04-11.1) p = .04]. Model AUC was 0.84 (compared to 0.79 without ECG-derived AF probability) and chi square was 61 (compared to 43 without ECG-derived AF probability, p <.001).
Conclusion
A clinical risk model based on AI-ECG, age and free T4 was strongly associated with developing GD-associated AF at follow-up. The AI-enabled ECG is available within the electronic medical record and could be easily incorporated in clinical-decision tools. Prospective validation of the model is currently underway.