Enhancing heart disease classification with M2MASC and CNN-BiLSTM integration for improved accuracy

Area of Science:

• Cardiology
• Artificial Intelligence
• Data Science

Background:

• Heart disease is a major global health concern, necessitating accurate detection and classification methods.
• Traditional machine learning and deep learning models face challenges like overfitting, underfitting, and data scarcity.
• Existing methods may lack robust data security and privacy mechanisms.

Purpose of the Study:

• To develop an advanced model for heart disease detection and classification.
• To enhance predictive accuracy and overcome limitations of classical approaches.
• To ensure data security, transparency, and privacy in heart disease prediction systems.

Main Methods:

• Proposed a Modified mixed attention-enabled search optimizer-based CNN-Bidirectional Long Short-Term Memory (M2MASC enabled CNN-BiLSTM) model.
• Integrated blockchain technology for secure and transparent data management.
• Utilized Internet of Things (IoT) devices for real-time patient data collection.
• Incorporated a pre-trained VGG16 model for improved feature extraction.

Main Results:

• The M2MASC enabled CNN-BiLSTM model achieved high performance metrics.
• Achieved an accuracy of 98.25%, precision of 99.57%, and recall of 97.53% on the MIT-BIH dataset.
• Demonstrated superior performance compared to traditional heart disease detection methods.

Conclusions:

• The proposed integrated model offers a secure, transparent, and highly accurate solution for heart disease detection and classification.
• Blockchain and IoT integration enhance data integrity and enable real-time monitoring.
• The M2MASC enabled CNN-BiLSTM model represents a significant advancement in AI-driven cardiovascular diagnostics.