Deep learning based cardiac disorder classification and user authentication for smart healthcare system using ECG...

Area of Science:

• Cardiology
• Biomedical Engineering
• Artificial Intelligence

Background:

• Timely diagnosis of abnormal cardiac activity is critical for preventing severe health complications and saving lives.
• Intelligent telehealth systems offer remote, non-invasive monitoring of cardiac diseases, transforming healthcare delivery.
• Internet of Things (IoT)-enabled electrocardiogram (ECG) monitors are key to gathering and analyzing cardiac data for early detection.

Purpose of the Study:

• To develop an efficient deep learning model for classifying cardiovascular problems using ECG data.
• To enhance the precision and classification accuracy of cardiac disorder detection.
• To implement a secure telehealth system with user identification capabilities using ECG signals.

Main Methods:

• A cloud-based telehealth system integrated with IoT-enabled ECG monitors was utilized.
• Deep learning models, specifically Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), were employed for ECG signal analysis.
• Data preprocessing and augmentation techniques were applied to improve data quality and quantity for model training.

Main Results:

• The proposed LSTM model achieved 99.5% accuracy in classifying cardiac diseases.
• The LSTM model demonstrated 98.6% accuracy in user authentication using ECG signals.
• The developed system showed superior performance compared to conventional machine learning and CNN models.

Conclusions:

• The intelligent telehealth system effectively categorizes and detects cardiovascular problems with high accuracy.
• The system enhances security and privacy through reliable user identification via ECG data.
• This approach signifies a significant advancement in remote cardiac monitoring and diagnosis.