MKELM: Mixed Kernel Extreme Learning Machine using BMDA optimization for web services based heart disease prediction...

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Cardiology

Background:

• Cardiovascular diseases are a leading cause of mortality globally.
• Early detection of heart disease is critical for effective patient management and prevention of adverse events.
• Current methods often face challenges due to delayed diagnosis.

Purpose of the Study:

• To propose a smart healthcare method for accurate heart disease prediction.
• To leverage machine learning with advanced optimization techniques for improved diagnostic capabilities.
• To address the limitations of delayed disease identification in cardiac patients.

Main Methods:

• A novel approach, Biogeography optimization algorithm and Mexican hat wavelet to enhance Dragonfly algorithm optimization with mixed kernel based extreme learning machine (BMDA-MKELM), was developed.
• Patient data was collected from sensor nodes and electronic medical records using an Android-based design.
• A cloud-based scheme facilitated reliable data storage and retrieval for analysis.

Main Results:

• The proposed BMDA-MKELM scheme demonstrated capability in classifying cardiovascular diseases.
• Performance evaluation showed superior accuracy, precision, specificity, and sensitivity compared to existing methods.
• Experimental results confirmed the effectiveness of the developed prediction scheme.

Conclusions:

• The BMDA-MKELM approach offers a significant advancement in the early prediction of cardiovascular diseases.
• The integration of advanced optimization algorithms and cloud computing enhances the reliability and accuracy of heart disease diagnosis.
• This smart healthcare solution holds promise for improving patient outcomes by enabling timely intervention.