Integration of Multiple Regression Model in an Epidemiological Decision Support System

Abstract

Prevention and control of influenza epidemics are major challenges for public health care services. Early identification of flu outbreak is an important step towards implementing effective disease interventions for reducing mortality and morbidity in human populations. Indeed, health officials need a real geo-making tool for monitoring and prediction. The aim of the current study is to discuss a novel spatiotemporal tool for monitoring and predicting the phenomenon of the seasonal influenza epidemic spread in the human population using multiple regression analysis. The suggested tool is mainly based on three sub-systems. It allows generating simulation data by the use of a simulation system, integrating data sources in a data warehouse (DW) system and performing a specific online analysis Spatial On-Line Analytical Processing (SOLAP). Our proposal enables also to illustrate evolution of disease through visualizations in time and space. It can examine social network effects to better understand the topological structure of social contact and the impact of its properties. A regression analysis is performed on the influenza epidemic to examine the main factors influencing flu incidence number and therefore to predict and track influenza epidemic.