Privacy-based framework for Cyber Resilience of Healthcare based data for use with Machine Learning algorithms

Cyber resilience is the business capability of handling the risks and preparing themselves for responding and recovering from risks. Being a cyber resilient the organization is capable of handling unknown or less known threats and ready to face such adversities and challenges. Healthcare related datasets using Machine learning or ML-based systems for detection of diseases such as Streptococcus pharyngitis will be expected to operate in contested and adversarial environments. Every operation these datasets support depends on their capacity to adjust to threats. To minimize the risk of misdiagnosing and early diagnosis of the disease an intelligent ML method are required. ML has gained a significant success in almost all the domains and has proved its ability in healthcare sector also. This research presents comparison of different ML algorithms to detect Pharyngitis. The study revealed that with reduced feature set Random Forest performs best with 70.11% accuracy and outshined all other implemented techniques. The authors propose a new privacy framework to protect the patient health care data.