Abstract
Understanding and modeling the mobility of individuals is of paramount importance for public health. In particular, mobility characterization is key to predict the spatial and temporal diffusion of human-transmitted infections. However, the mobility behavior of a person can also reveal relevant information about her/his health conditions. In this paper, we study the impact of people mobility behaviors for predicting the future presence of flu-like and cold symptoms (i.e. fever, sore throat, cough, shortness of breath, headache, muscle pain, malaise, and cold). To this end, we use the mobility traces from mobile phones and the daily self-reported flu-like and cold symptoms of 29 individuals from February 20, 2013 to March 21, 2013. First of all, we demonstrate that daily symptoms of an individual can be predicted by using his/her mobility trace characteristics (e.g. total displacement, radius of gyration, number of unique visited places, etc.). Then, we present and validate models that are able to successfully predict the future presence of symptoms by analyzing the mobility patterns of our individuals. The proposed methodology could have a societal impact opening the way to customized mobile phone applications, which may detect and suggest to the user specific actions in order to prevent disease spreading and minimize the risk of contagion.
Highlights
Nowadays, we leave traces of our life events, behaviors, interests, and habits on social networks (e.g. Facebook statuses and tweets), using mobile phones and surfing the web
We found that Recursive Feature Elimination (RFE) is the bestperforming feature selection method when using Logistic Regression (LR), Random Forest (RF), and Gradient Boosted Trees (GBT)
We report in Table the confusion matrix for the case thist = and thor = using Gradient Boosted Trees (GBT), which refers to the best results in the setting of predicting future presence of flu-like and cold symptoms, i.e. one day ahead
Summary
We leave traces of our life events, behaviors, interests, and habits on social networks (e.g. Facebook statuses and tweets), using mobile phones and surfing the web. All this information together works as a powerful microscope that can help us to understand and predict many phenomena of our society. The world coverage has raised from % of the world population in up to % in [ ], and this number even reaches % of population in the developed countries These devices generate an incredible amount of data on how we daily use our mobile phone and how we interact with other people. They contain location data (e.g. from where a person calls) that makes people’s movements
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call