Assessment of the atrial fibrillation burden in Holter electrocardiogram recordings using artificial intelligence
Elisa Hennings, Michael Coslovsky, Rebecca E. Paladini, Stefanie Aeschbacher, Sven Knecht, Vincent Schlageter, Philipp Krisai, Patrick Badertscher, Christian Sticherling, Stefan Osswald, Michael Kühne, Christine S. Zuern
Abstract
BackgroundEmerging evidence indicates that a high atrial fibrillation (AF) burden is associated with adverse outcome. However, AF burden is not routinely measured in clinical practice. An artificial intelligence (AI)-based tool could facilitate the assessment of AF burden.ObjectiveWe aimed to compare the assessment of AF burden performed manually by physicians with that measured by an AI-based tool.MethodsWe analyzed 7-day Holter electrocardiogram (ECG) recordings of AF patients included in the prospective, multicenter Swiss-AF Burden cohort study. AF burden was defined as percentage of time in AF, and was assessed manually by physicians and by an AI-based tool (Cardiomatics, Cracow, Poland). We evaluated the agreement between both techniques by means of Pearson correlation coefficient, linear regression model, and Bland-Altman plot.ResultsWe assessed the AF burden in 100 Holter ECG recordings of 82 patients. We identified 53 Holter ECGs with 0% or 100% AF burden, where we found a 100% correlation. For the remaining 47 Holter ECGs with an AF burden between 0.01% and 81.53%, Pearson correlation coefficient was 0.998. The calibration intercept was -0.001 (95% CI -0.008; 0.006), and the calibration slope was 0.975 (95% CI 0.954; 0.995; multiple R2 0.995, residual standard error 0.017). Bland-Altman analysis resulted in a bias of -0.006 (95% limits of agreement -0.042 to 0.030).ConclusionThe assessment of AF burden with an AI-based tool provided very similar results compared to manual assessment. An AI-based tool may therefore be an accurate and efficient option for the assessment of AF burden. Emerging evidence indicates that a high atrial fibrillation (AF) burden is associated with adverse outcome. However, AF burden is not routinely measured in clinical practice. An artificial intelligence (AI)-based tool could facilitate the assessment of AF burden. We aimed to compare the assessment of AF burden performed manually by physicians with that measured by an AI-based tool. We analyzed 7-day Holter electrocardiogram (ECG) recordings of AF patients included in the prospective, multicenter Swiss-AF Burden cohort study. AF burden was defined as percentage of time in AF, and was assessed manually by physicians and by an AI-based tool (Cardiomatics, Cracow, Poland). We evaluated the agreement between both techniques by means of Pearson correlation coefficient, linear regression model, and Bland-Altman plot. We assessed the AF burden in 100 Holter ECG recordings of 82 patients. We identified 53 Holter ECGs with 0% or 100% AF burden, where we found a 100% correlation. For the remaining 47 Holter ECGs with an AF burden between 0.01% and 81.53%, Pearson correlation coefficient was 0.998. The calibration intercept was -0.001 (95% CI -0.008; 0.006), and the calibration slope was 0.975 (95% CI 0.954; 0.995; multiple R2 0.995, residual standard error 0.017). Bland-Altman analysis resulted in a bias of -0.006 (95% limits of agreement -0.042 to 0.030). The assessment of AF burden with an AI-based tool provided very similar results compared to manual assessment. An AI-based tool may therefore be an accurate and efficient option for the assessment of AF burden.