Patient privacy in smart cities by blockchain technology and feature selection with Harris Hawks Optimization (HHO)...

Area of Science:

• Health Informatics
• Cybersecurity in Healthcare
• Artificial Intelligence in Medicine

Background:

• Smart cities require secure and confidential medical data exchange for accurate patient treatment.
• Current methods of sharing medical data between centers often lack adequate confidentiality.
• Protecting patient privacy is a fundamental principle in medical practice.

Purpose of the Study:

• To propose a novel two-layer framework for secure and confidential medical data transmission between healthcare centers.
• To leverage blockchain for secure data transmission and machine learning for enhanced diagnostics.
• To improve the accuracy and reliability of disease diagnosis through collaborative expert opinion and data analysis.

Main Methods:

• A two-layer framework utilizing blockchain for secure data transmission and machine learning for data analysis.
• Patient records are stored in blocks on a blockchain and shared among medical centers.
• A binary version of the HHO algorithm is used for feature selection, and majority voting learning is employed for disease diagnosis.

Main Results:

• The proposed blockchain-based system achieves approximately 100% data confidentiality.
• The framework demonstrates significantly higher reliability and dependability compared to centralized methods.
• For heart disease diagnosis, the method achieved an accuracy of 92.75%, sensitivity of 92.15%, and precision of 95.69%, outperforming other machine learning models.

Conclusions:

• The proposed framework effectively ensures the confidentiality and security of medical data transmission in smart cities.
• The integration of blockchain and machine learning enhances diagnostic accuracy and reliability in healthcare.
• This approach offers a superior alternative to traditional centralized methods for medical data sharing and analysis.