Blockchain enabled deep learning model with modified coati optimization for sustainable healthcare disease detection...

Area of Science:

• Healthcare Informatics
• Artificial Intelligence in Medicine
• Data Security in Healthcare

Background:

• Increasing patient numbers and complex diseases challenge traditional health monitoring.
• Managing big, heterogeneous health data and ensuring patient privacy are critical issues.
• Early disease prediction and accurate classification are vital for effective healthcare.

Purpose of the Study:

• To propose an efficient and accurate disease detection and classification method for healthcare.
• To leverage deep learning techniques for improved diagnostic capabilities.
• To enhance data security and management in healthcare through blockchain technology.

Main Methods:

• The Modified Coati Optimization Driven Blockchain for Healthcare Disease Detection and Classification (MCODBC-HDDC) method integrates blockchain for secure data.
• Data preprocessing includes Z-score normalization, and feature selection is performed using the Spotted Hyena Optimization Algorithm (SHOA).
• Disease detection and classification utilize an Attention Bidirectional Gated Recurrent Unit (ABiGRU) optimized by the Modified Coati Optimization Algorithm (MCOA).

Main Results:

• The MCODBC-HDDC method demonstrated superior performance in disease detection and classification.
• Experimental analysis on the HD dataset yielded an accuracy of 97.36%.
• The approach provides a secure, decentralized, and tamper-proof environment for patient data management.

Conclusions:

• The MCODBC-HDDC method offers a significant advancement in AI-driven healthcare diagnostics.
• The integration of blockchain and deep learning enhances accuracy and data security.
• This approach holds promise for improving patient outcomes through early and precise disease identification.