A Framework for Healthcare Management System Using Predictive Analysis of Diseases

Abstract

Disease outbreak detection is a major challenge in public health informatics. While big data in healthcare is constantly expanding, there still exists a need to effectively integrate and represent data in order to obtain useful information applicable in solving disease outbreak problems. This study presents a framework to analyze the disease outbreaks for a given population by performing predictive analytics on incidence data. This information is particularly useful for the decision-makers in the context of healthcare management to formulate intervention programs based on the results. None of the existing public health frameworks that support the integration of predictive analysis with decision making process for optimal resource planning and control. We present data acquisition and transmission framework with a predictive analytics on top to provide threshold based alert to decision-makers on disease incidence data. We use a temporal predictive Auto-Regressive Integrated Moving Averaging model (ARIMA) in combination with a minimum size moving window to forecast the disease incidences over a data collection and integration framework. We applied our model for predictive analysis of Hepatitis C incidences in Lahore and Vehari District of Punjab province in Pakistan. Model performance is evaluated based on Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). The results of the analysis provide a sound reference for expanding capabilities of the disease management tools in healthcare management context.