Design of Smart and Secured Healthcare Service Using Deep Learning with Modified SHA-256 Algorithm

Area of Science:

• Medical Informatics
• Artificial Intelligence in Healthcare
• Cybersecurity in Healthcare

Background:

• Modern healthcare faces rising disease burdens and associated mortality, necessitating robust health and financial management.
• Securing sensitive patient and financial data is crucial to prevent wealth loss and ensure genuine care.
• Existing systems often lack comprehensive security for diverse medical data types.

Purpose of the Study:

• To design a secure hospital management system with advanced data processing capabilities.
• To develop an effective smart healthcare system for brain tumor patients, ensuring data privacy.
• To enhance the security of medical insurance data processing and combat healthcare fraud.

Main Methods:

• A three-phase approach: smart healthcare application for remote patient access, deep learning for brain tumor detection (MRI/EEG), and a modified SHA-256 algorithm for secure insurance data encryption.
• Development of an Android and Microsoft-compatible application for patient registration, diagnosis, pathology, admission, and insurance services.
• Modification of the SHA-256 algorithm for long data encryption, generating a long key for enhanced security of financial and medical records.

Main Results:

• Deep learning models achieved high accuracy in diagnostic predictions, aiding admission decisions.
• Patient data entered into the system is encrypted using a 256-bit hash value for secure data management.
• The modified SHA-256 algorithm provides enhanced security for long medical insurance data.

Conclusions:

• The proposed system offers a secure and efficient solution for hospital management and patient data protection.
• Deep learning integration improves diagnostic accuracy for conditions like brain tumors.
• Enhanced encryption methods significantly bolster the security of medical insurance data, reducing fraud potential.