|Start:||01 January 2013|
|End:||30 May 2013|
|Department:||Mobile Networks (MONET)|
Seasonal infectious diseases like influenza are responsible of significant morbidity and mortality every year. The World Health Organization (WHO) estimates that annual influenza epidemics result in about 3 to 5 million cases of severe illness and about 250,000 to 500,000 casualties worldwide. Surveillance systems that timely detect disease outbreaks can play a key role in limiting the spread of the disease and its impact.
In developed countries, surveillance system like sentinel networks covering small portion of the population and, more recently, electronic medical records are successfully employed. However, these systems require very costly infrastructures. Developing countries such as Ivory Coast cannot deploy these systems because of their cost. On the other hand, if it were possible to build a disease outbreak surveillance system that uses existing non-medical monitoring infrastructures (such as a mobile network infrastructure), its cost would be lower and a developing country could afford it.
In this project we aim at developing a system that provides an automated detection of epidemics of infectious diseases based on the analysis of mobile network traffic and mobility patterns. The objective is to build an autonomous detection algorithm that is able to determine whether certain infectious diseases in Ivory Coast are active or not based on the datasets provided by Orange. To design and test this algorithm, medical data from other sources (e.g., data provided by the WHO) will be employed. The performance of the algorithm will be evaluated considering aspects such as sensitivity and timeliness of the detection.