An optimal healthcare self-diagnosis system using cloud framework

The disease diagnosis is more complex task for any healthcare practices. The human body is quite complicated in analyzing any kind of misbehaviors. Apparently, our daily life is completely uncertain and unpredictable. In accordance to this stringent situation, the identification and diagnosis is becomes very tedious process. In this paper, we anticipated an optimal and simple self-diagnostics cloud based system for predicting the diseases precisely. The cloud based framework is integrated with various cloud storage and processing nodes which contains enormous disease-symptom lattice structure. We have proposed an A∗(A-Star) deep searching algorithm to extract correlated combination of disease-symptoms data from various cloud nodes. The Bitap algorithm is for selection of best possible cloud clusters. Based on the extracted information the formal context where build. Finally the optimal and data analysis and diagnostic algorithm will predict precise disease. However the recommended model is fully depend on the user data (Symptom definition). The incorrect combination of symptoms will lead to be wrong or worst predictions. The projected model is evaluated through simulated environment. The best possible results has exhibited.