What is the clinical evidence from this study?

Study design: Other. Population: Cardiovascular Disease (n=303). Intervention: Edge-AI Cardiac Decision Support System vs. Existing cardiac diagnostic methods. Primary outcome: Accuracy of cardiac disease diagnosis (p=<0.001).

What question did this study set out to answer?

The research aims to improve cardiac decision support systems using edge AI and efficient deep learning methods.

January 10, 2026INTERNATIONAL JOURNAL OF ENGINEERING DEVELOPMENT AND RESEARCH0 citationsOpen Access

An Edge AI Enabled IoT Cardiac Decision Support System Using RF Fuzzy Feature Selection and Efficient Deep Neural Networks

Q: What are the key findings of this study?

The Edge-AI enabled cardiac decision support system achieved 99.4% accuracy, significantly outperforming existing methods.

Q: What question did this study set out to answer?

The research aims to improve cardiac decision support systems using edge AI and efficient deep learning methods.

MMMathan.S Mathan.S SGSunil GuptaJaipur National University

Key Result

The Edge-AI enabled cardiac decision support system achieved 99.4% accuracy, significantly outperforming existing methods.

Key Points

The research aims to improve cardiac decision support systems using edge AI and efficient deep learning methods.
Utilized edge AI technology for real-time data processing
Implemented RF fuzzy feature selection for enhanced data accuracy
Developed a deep neural network model for decision support
The system showed increased accuracy in cardiac assessments
Improved decision-making speed by reducing processing latency
Achieved higher user satisfaction in IoT applications

Structured PICO

Population

303 patient records from the UCI Heart Disease dataset (Cleveland Clinic Foundation)

Intervention

Edge-AI enabled cardiac decision support system using Random Forest (RF) feature selection, fuzzy logic optimization, and a Deep Neural Network (DNN)

Comparator

Baseline models without optimization and 13 state-of-the-art machine learning methods from recent literature

Outcome

Classification accuracy, precision, recall, F1-score, specificity, and AUC for predicting cardiac risk levels (Normal, Mild, Moderate, Severe)surrogate

An edge-AI framework combining Random Forest feature selection, fuzzy logic, and a lightweight DNN achieved 99.4% accuracy in cardiac disease classification on a benchmark dataset while remaining efficient enough for IoT deployment.

Main Result

p-value: p=<0.001

Limitations

Dataset size (303 samples) limits generalizability
Real-world IoT sensors may introduce additional noise
Requires prospective clinical outcome studies.

Abstract

Cardiovascular disease (CVD) is the leading cause of global mortality, responsible for approximately 17.9 million deaths each year. This underscores the need for early, accurate, and scalable diagnostic solutions. As IoT-enabled healthcare and edge computing become more prevalent, there is growing interest in intelligent cardiac decision support systems that can operate under resource constraints. This study introduces an Edge-AI–assisted cardiac diagnosis framework that combines Random Forest (RF)–based feature selection, fuzzy logic–driven feature optimization, and an efficient Deep Neural Network (DNN) classifier. The framework is validated using the UCI Heart Disease dataset. RF selects the most relevant clinical features, reducing dimensionality and computational cost while preserving essential diagnostic information. Gaussian fuzzy membership functions, developed with clinical expertise, address uncertainty in physiological data and optimize the selected features. A lightweight DNN enables low-latency, energy-efficient real-time inference at the edge. The system achieves 99.4% accuracy, 98.7% precision, 97.9% recall, and an AUC of 0.998. This approach is well suited for IoT healthcare applications, including wearable sensors, WBANs, and edge computing environments, providing a scalable, interpretable, and practical solution for resource-limited healthcare systems.

Ask AI

Helpful

Bookmark

View Full Paper