HyCARD-Net: A Synergistic Hybrid Intelligence Framework for Cardiovascular Disease Diagnosis

2025-11-21

2025 4th International Conference on Image Processing, Computer Vision and Machine Learning (ICICML)

AI Summary

This study addresses the limited generalization capability of existing cardiovascular disease prediction models when confronted with heterogeneous data and complex physiological patterns, which hinders accurate early diagnosis. To overcome this challenge, the authors propose a hybrid intelligent framework that integrates deep learning architectures—specifically CNNs and LSTMs—with classical machine learning methods such as KNN and XGBoost. By leveraging an ensemble voting mechanism, the framework synergistically enhances predictive performance while uniquely combining the strong representational power of deep models with the interpretability of traditional approaches. The resulting diagnostic paradigm demonstrates high robustness and clinical applicability. Evaluated on two public Kaggle datasets, the model achieves accuracy rates of 82.30% and 97.10%, respectively, significantly outperforming current baseline methods.

Technology Category

• Machine Learning: Ensemble Methods
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Cardiovascular disease (CVD) remains the foremost cause of mortality worldwide, underscoring the urgent need for intelligent and data-driven diagnostic tools. Traditional predictive models often struggle to generalize across heterogeneous datasets and complex physiological patterns. To address this, we propose a hybrid ensemble framework that integrates deep learning architectures—Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM)—with classical machine learning algorithms, including K-Nearest Neighbor (KNN) and Extreme Gradient Boosting (XGB), using an ensemble voting mechanism. This approach combines the representational power of deep networks with the interpretability and efficiency of traditional models. Experiments on two publicly available Kaggle datasets demonstrate that the proposed model achieves superior performance, reaching 82.30% accuracy on Dataset I and 97.10% on Dataset II, with consistent gains in precision, recall, and F1-score. These findings underscore the robustness and clinical potential of hybrid AI frameworks for predicting cardiovascular disease and facilitating early intervention. Furthermore, this study directly supports the United Nations Sustainable Development Goal 3 (Good Health and Well-being) by promoting early diagnosis, prevention, and management of non-communicable diseases through innovative, data-driven healthcare solutions.

Problem

• Cardiovascular Disease
• Diagnostic Generalization
• Heterogeneous Data
• Predictive Modeling
• Early Intervention

Innovation

• hybrid intelligence
• ensemble learning
• cardiovascular disease diagnosis
• deep learning
• machine learning