Constraint-Based Model in Multimodal Learning to Improve Ventricular Arrhythmia Prediction

TL;DR

This paper proposes a constraint-based multimodal learning model using a novel Sequential Fusion technique to improve ventricular arrhythmia prediction by effectively combining clinical and CT imaging data.

Contribution

It introduces a new Sequential Fusion method and demonstrates its superior performance over traditional fusion techniques in VA prediction.

Findings

Sequential Fusion outperforms Early Fusion in sensitivity and F1 score.

Fusion models outperform single-modality models in VA prediction.

The proposed approach achieves an average sensitivity of 80.7% and F1 score of 73.1%.

Abstract

Cardiac disease evaluation depends on multiple diagnostic modalities: electrocardiogram (ECG) to diagnose abnormal heart rhythms, and imaging modalities such as Magnetic Resonance Imaging (MRI), Computed Tomography (CT) and echocardiography to detect signs of structural abnormalities. Each of these modalities brings complementary information for a better diagnosis of cardiac dysfunction. However, training a machine learning (ML) model with data from multiple modalities is a challenging task, as it increases the dimension space, while keeping constant the number of samples. In fact, as the dimension of the input space increases, the volume of data required for accurate generalisation grows exponentially. In this work, we address this issue, for the application of Ventricular Arrhythmia (VA) prediction, based on the combined clinical and CT imaging features, where we constrained the learning process on medical images (CT) based on the prior knowledge acquired from clinical data. The VA classifier is fed with features extracted from a 3D myocardium thickness map (TM) of the left ventricle. The TM is generated by our pipeline from the imaging input and a Graph Convolutional Network is used as the feature extractor of the 3D TM. We introduce a novel Sequential Fusion method and evaluate its performance against traditional Early Fusion techniques and single-modality models. The crossvalidation results show that the Sequential Fusion model achieved the highest average scores of 80.7% $\pm$ 4.4 Sensitivity and 73.1% $\pm$ 6.0 F1 score, outperforming the Early Fusion model at 65.0% $\pm$ 8.9 Sensitivity and 63.1% $\pm$ 6.3 F1 score. Both fusion models achieved better scores than the single-modality models, where the average Sensitivity and F1 score are 62.8% $\pm$ 10.1; 52.1% $\pm$ 6.5 for the clinical data modality and 62.9% $\pm$ 6.3; 60.7% $\pm$ 5.3 for the medical images modality.