Document Type : Research Note

Authors

• vahidreza afshin ¹
• Saiedeh Kabirirad ¹
• Seyed Hamid Zahiri ²

¹ Department of Computer Science, Birjand University of Technology, Birjand, Iran.

² Department of Electrical Engineering, Faculty of Engineering, University of Birjand, Birjand, Iran

Abstract

Accurate and timely detection of heart disease is a fundamental challenge in clinical diagnostics, exacerbated by the inherent complexities of real-world healthcare datasets, such as class imbalance, high dimensionality and the presence of outliers. To address these issues, we propose a dual-path learning framework specifically designed for real-time heart disease detection within IoT–Fog–Cloud environments. The framework integrates advanced preprocessing techniques, including Conditional Generative Adversarial Networks (CGANs) for data balancing and a hybrid feature selection pipeline, thereby addressing data imbalance and dimensionality reduction. It also proposes a dual-path diagnostic system that uses a lightweight XGBoost classifier in the fog layer optimized for low latency and fast local inference, and an improved TabTransformer-based model in the cloud layer, which is selectively used for ambiguous samples. Experimental evaluation on heart disease datasets demonstrates the superior performance of the framework, achieving 99.66% accuracy, F1 score of 99.75%, and AUC of 99.96%. Additionally, it improves overall inference latencies, mostly below one millisecond in the fog layer and low latency in cloud layer. This paper provides a scalable, interpretable, and privacy-preserving medical diagnosis framework in distributed healthcare systems.

Keywords

• Heart Disease Detection
• IoT–Fog–Cloud Computing
• CGAN-based Data Balancing Hybrid Feature Selection
• XGBoost
• TabTransformer

Main Subjects

• H.3. Artificial Intelligence