HealthAnalytic: A concept application for customizable visualization and analysis of health informatics datasets

A large amount of health statistics of the Indian population has recently become available in the public domain owing to the National Data Sharing and Accessibility Policy (NDSAP). This statistical data is beneficial if it can be used to obtain meaningful inferences from data-driven models. Analysis and visualization of such data has been a challenge and has become an imperative requirement for executive decision making. The challenge could be attributed to the fact that the set of features that an attribute is dependent on is subjective and data-dependent. Hence, there is a need to provide a pervasive and flexible data analytics framework that would allow this data to drive decision making. We propose a concept for the design and development of a fully customizable data analysis framework on the Android platform which allows users to visualize the effect of any combination of attributes drawn from these datasets in predicting a particular attribute (label). We use feature scoring techniques to achieve this, and also provide an additional option to view data correlation. The intended application, called HealthAnalytic, is beneficial for executive level decision-making, as it provides visualization via data-driven models along with the pervasiveness of a mobile application. The initial version of the application uses existing methods, however newer scalable methods can be incorporated in the future.