Atrial fibrillation prediction by combining ECG markers and CMR radiomics

Abstract

Atrial fibrillation (AF) is the most common cardiac arrhythmia. It is associated with a higher risk of important adverse health outcomes such as stroke and death. AF is linked to distinct electro-anatomic alterations. The main tool for AF diagnosis is the Electrocardiogram (ECG). However, an ECG recorded at a single time point may not detect individuals with paroxysmal AF. In this study, we developed machine learning models for discrimination of prevalent AF using a combination of image-derived radiomics phenotypes and ECG features. Thus, we characterize the phenotypes of prevalent AF in terms of ECG and imaging alterations. Moreover, we explore sex-differential remodelling by building sex-specific models. Our integrative model including radiomics and ECG together resulted in a better performance than ECG alone, particularly in women. ECG had a lower performance in women than men (AUC: 0.77 vs 0.88, p < 0.05) but adding radiomics features, the accuracy of the model was able to improve significantly. The sensitivity also increased considerably in women by adding the radiomics (0.68 vs 0.79, p < 0.05) having a higher detection of AF events. Our findings provide novel insights into AF-related electro-anatomic remodelling and its variations by sex. The integrative radiomics-ECG model also presents a potential novel approach for earlier detection of AF.

Figure 1

Correlation between ECG and radiomics features showing low correlation between radiomics features extracted from the short-axis images and a slightly higher correlation with the features from the long axis images including atrial metrics. Temp temporal, Freq frequency, HRV heart rate variability, HR heart rate.

Figure 2

The figure shows four-chamber cine CMR images in end-diastole from two female UK Biobank participants. Our models selected the most important radiomics features from the left atrial region of interest. The arrows show the axis, and the circular shape indicates the sphericity. The first image (a) shows an AF patient with a larger axis and pronounced oval sphericity. The second image (b) illustrates a healthy subject with normal atrial dimensions, with more circular sphericity and a smaller axis than an AF patient.

Figure 3

Different random partitions of the healthy cohort were randomly selected to show the added value of radiomics versus ECG alone in women. For all the cases, the improvement is clear and statistically significant (p < 0.05).

Figure 4

The process to select the data from the UK Biobank.

Figure 5

A nested cross validation scheme.