Related Experiment Videos
An IoT-enabled heart disease prediction framework using hybrid and multi-dilated convolution aided adaptive residual
A Moorthy1, V Sarala1, C Sivasankar2
1Department of Computer Science and Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences (SIMATS), Saveetha University, Chennai, Tamil Nadu, 602105, India.
Physical and Engineering Sciences in Medicine
|April 21, 2026
Summary
This study introduces an Internet of Things (IoT)-based network for precise heart disease detection. The developed Hybrid and Multi-dilated Convolution based Adaptive Residual Attention Network (HMDCARAN) achieves high accuracy in early heart disorder identification.
Area of Science:
- Medical Informatics
- Biomedical Engineering
- Artificial Intelligence in Healthcare
Background:
- The digital era generates vast patient data, overwhelming manual processing by physicians.
- Efficient heart disease detection and continuous expert consultation remain challenging, contributing to rising mortality rates.
- Accurate and precise prediction of heart disease is critical to prevent severe outcomes.
Purpose of the Study:
- To develop an Internet of Things (IoT)-based network for early and accurate heart disease detection.
- To address limitations in current methods for real-time monitoring and expert consultation.
- To improve the precision of heart disease prediction, reducing risks associated with delayed diagnosis.
Main Methods:
- A two-phase approach was implemented, starting with signal collection and conversion to spectrogram images using Short-Time Fourier Transform.
- Sensor data was collected via IoT devices in the second phase.
- A Hybrid and Multi-dilated Convolution based Adaptive Residual Attention Network (HMDCARAN), optimized by the Modified Crayfish Optimization Algorithm, was utilized for prediction.
Main Results:
- The HMDCARAN framework achieved high performance metrics: 96.52% accuracy, 98.29% precision, and 97.18% sensitivity.
- These results demonstrated superior effectiveness compared to traditional approaches.
- The developed network successfully identified heart disease in its initial stages.
Conclusions:
- The proposed IoT-based network and HMDCARAN model offer a significant advancement in early heart disease detection.
- The system effectively overcomes risk factors associated with advanced heart disorders.
- This approach holds promise for personalized medical care and improved patient outcomes.