Understanding the Impact of Socio-Economic and Environmental Factors for Disease Outbreak in Developing Countries

The growing impact of disease outbreaks has emphasized the need for data mining and machine learning techniques for their analysis and prediction. To do this effectively an elaborate and reliable data management system is required. Unfortunately, such systems do not exist in many developing countries where the available information can be sparse and noisy with important factors missing from the data. In this paper, we report on the study of three diseases and their outbreaks in a developing country (Pakistan) with the goal of gaining a better understanding of environmental/weather and socio-economic factors that impact them. The data available from local health units contained only numbers of reported cases from different localities. We first enrich this data by fusing key environmental and socio-economic factors obtained from other sources. We then perform independent factor analysis of the augmented data, using decision tree and logistic regression. We study cross-disease and cross-locality impacts, and show the effectiveness of an outbreak prediction model. Our results highlight combinations of factors influencing disease outbreaks that can guide administrators towards their mitigation.