Knowledge Gaps in Hybrid Deep Learning-Based Cardiovascular Disease Prediction Systems: A Critical Analysis
Contributors
Neeraj Varshney
PAWAN
Keywords
Proceeding
Track
General Track
License
Copyright (c) 2026 Sustainable Global Societies Initiative

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Abstract
Cardiovascular diseases (CVDs) remain a major global health concern, creating a strong need for accurate, automated, and reliable prediction and diagnostic systems. Recent developments in Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) have significantly advanced the automated analysis of electrocardiogram (ECG) signals. Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Transformers, attention mechanisms, and hybrid architectures have demonstrated promising performance in cardiovascular disease and arrhythmia classification. However, high predictive performance reported on benchmark datasets does not necessarily resolve the practical and clinical challenges associated with cardiovascular prediction. The critical analysis of existing studies reveals several important knowledge gaps, including limited integration of multimodal healthcare information, class imbalance and rare arrhythmia detection, poor generalization across datasets, limited explainability, high computational complexity, insufficient real-world clinical validation, and the difficulty of simultaneously achieving accuracy, interpretability, robustness, and deployment efficiency. Existing hybrid models frequently combine two or more deep learning architectures, but an integrated and practically deployable framework addressing these challenges simultaneously remains insufficiently established. This paper critically analyses the major knowledge gaps identified from existing hybrid deep learning-based cardiovascular prediction systems and consolidates them into a broader research gap. The identified gaps provide a foundation for defining appropriate methods and experimental investigations in subsequent stages of the research.