Title : Application of AI in the detection of cardiovascular disease using multimodal imaging – a literature review
Abstract:
Background/Context: Cardiovascular disease (CVD) remains the leading cause of mortality worldwide and places a considerable burden on healthcare systems. Accurate and timely detection is vital for improving clinical outcomes, yet conventional imaging interpretation is limited by subjectivity, variability, and time constraints. Artificial intelligence (AI), particularly deep learning (DL), is increasingly applied to address these challenges in cardiovascular imaging.
Aim or Objective: This review evaluates the use of AI in the detection and classification of CVD using multimodal imaging techniques—echocardiography, cardiac magnetic resonance imaging (CMR), and computed tomography
angiography (CCTA).
Methods: A systematic literature search was conducted across PubMed, IEEE Xplore, and Scopus for studies published between 2014 and 2025. Inclusion criteria focused on peer-reviewed studies applying AI to the selected imaging modalities for CVD detection and risk assessment.
Results: Convolutional neural networks consistently improve diagnostic accuracy, eSiciency, and risk prediction across modalities. However, the challenges include limited multimodal integration, generalisability across populations and imaging protocols, and the “black box” nature of DL models still.
Conclusions/Implications: AI has strong potential to transform cardiovascular diagnostics. Future research should prioritise explainable, multimodal, and prospectively validated models to support clinical adoption and enhance patient outcomes
