Secure aware software development life cycle on medical datasets by using firefly optimization and machine learning techniques

Abstract

The abstract highlights the critical need for securing sensitive medical data, emphasizing the challenges in the medical domain due to the confidentiality of patient, disease, doctor, and staff information. The proposed study introduces a novel approach using machine learning, specifically integrating the firefly optimization technique with the random forest algorithm, to classify medical data in a secure manner. The significance lies in addressing the security concerns associated with medical datasets, offering a solution that prioritizes confidentiality throughout the software development life cycle (SDLC). The proposed algorithm achieves an impressive accuracy of 96%, showcasing its efficacy in providing a robust and secure framework for the development of applications involving medical data. This research contributes to advancing the field of medical data security, offering a practical solution for safeguarding sensitive information in healthcare applications.