Unveiling Spatial Epidemiology of HIV with Mobile Phone Data

An increasing amount of geo-referenced mobile phone data enables the identification of behavioral patterns, habits and movements of people. With this data, we can extract the knowledge potentially useful for many applications including the one tackled in this study - understanding spatial variation of epidemics. We explored the datasets collected by a cell phone service provider and linked them to spatial HIV prevalence rates estimated from publicly available surveys. For that purpose, 224 features were extracted from mobility and connectivity traces and related to the level of HIV epidemic in 50 Ivory Coast departments. By means of regression models, we evaluated predictive ability of extracted features. Several models predicted HIV prevalence that are highly correlated (>0.7) with actual values. Through contribution analysis we identified key elements that correlate with the rate of infections and could serve as a proxy for epidemic monitoring. Our findings indicate that night connectivity and activity, spatial area covered by users and overall migrations are strongly linked to HIV. By visualizing the communication and mobility flows, we strived to explain the spatial structure of epidemics. We discovered that strong ties and hubs in communication and mobility align with HIV hot spots.

[1]  Sean D. Young,et al.  A "big data" approach to HIV epidemiology and prevention. , 2015, Preventive medicine.

[2]  A. Tatem,et al.  Population Distribution, Settlement Patterns and Accessibility across Africa in 2010 , 2012, PloS one.

[3]  G. Madey,et al.  Uncovering individual and collective human dynamics from mobile phone records , 2007, 0710.2939.

[4]  Yewon Kim,et al.  Solving Multicollinearity Problem Using Ridge Regression Models , 2015 .

[5]  Alessandro Vespignani,et al.  Multiscale mobility networks and the spatial spreading of infectious diseases , 2009, Proceedings of the National Academy of Sciences.

[6]  L. Zulu,et al.  HIV and AIDS in Africa: a geographic analysis at multiple spatial scales , 2010, GeoJournal.

[7]  Balázs Csanád Csáji,et al.  Exploring the Mobility of Mobile Phone Users , 2012, ArXiv.

[8]  L. Bengtsson,et al.  Improved Response to Disasters and Outbreaks by Tracking Population Movements with Mobile Phone Network Data: A Post-Earthquake Geospatial Study in Haiti , 2011, PLoS medicine.

[9]  W. Edmunds,et al.  Dynamic social networks and the implications for the spread of infectious disease , 2008, Journal of The Royal Society Interface.

[10]  N. Meda,et al.  Methods for mapping regional trends of HIV prevalence from Demographic and Health Surveys (DHS) , 2011 .

[11]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[12]  B. Lewis,et al.  Methods of using real-time social media technologies for detection and remote monitoring of HIV outcomes. , 2014, Preventive medicine.

[13]  Geoff P Garnett,et al.  Modelling the impact of migration on the HIV epidemic in South Africa , 2007, AIDS.

[14]  Timothy A. Thomas,et al.  Measures of Human Mobility Using Mobile Phone Records Enhanced with GIS Data , 2014, PloS one.

[15]  Licia Capra,et al.  Poverty on the cheap: estimating poverty maps using aggregated mobile communication networks , 2014, CHI.

[16]  Marcel Salathé,et al.  Validating models for disease detection using twitter , 2013, WWW.

[17]  Ryosuke Shibasaki,et al.  Understanding the unobservable population in call detail records through analysis of mobile phone user calling behavior: A case study of Greater Dhaka in Bangladesh , 2015, 2015 IEEE International Conference on Pervasive Computing and Communications (PerCom).

[18]  M. El-Dereny,et al.  Solving Multicollinearity Problem Using Ridge Regression Models , 2011 .

[19]  Aixia Guo,et al.  Gene Selection for Cancer Classification using Support Vector Machines , 2014 .

[20]  Marián Boguñá,et al.  Extracting the multiscale backbone of complex weighted networks , 2009, Proceedings of the National Academy of Sciences.

[21]  A. Rai,et al.  A smartphone dongle for diagnosis of infectious diseases at the point of care , 2015, Science Translational Medicine.

[22]  Cecilia Mascolo,et al.  A Tale of Many Cities: Universal Patterns in Human Urban Mobility , 2011, PloS one.

[23]  Alex Pentland,et al.  Once Upon a Crime: Towards Crime Prediction from Demographics and Mobile Data , 2014, ICMI.

[24]  Ramón Cáceres,et al.  A Tale of One City: Using Cellular Network Data for Urban Planning , 2011, IEEE Pervasive Computing.

[25]  Michael Emch,et al.  Spatial and socio-behavioral patterns of HIV prevalence in the Democratic Republic of Congo. , 2010, Social science & medicine.

[26]  Erik Strumbelj,et al.  A General Method for Visualizing and Explaining Black-Box Regression Models , 2011, ICANNGA.

[27]  Sean D. Young,et al.  Recommended Guidelines on Using Social Networking Technologies for HIV Prevention Research , 2012, AIDS and Behavior.

[28]  Jari Saramäki,et al.  Persistence of social signatures in human communication , 2012, Proceedings of the National Academy of Sciences.

[29]  Luis Miguel Romero Pérez,et al.  Traffic Flow Estimation Models Using Cellular Phone Data , 2012, IEEE Transactions on Intelligent Transportation Systems.

[30]  Etienne Huens,et al.  Data for Development: the D4D Challenge on Mobile Phone Data , 2012, ArXiv.

[31]  Vincent D. Blondel,et al.  A survey of results on mobile phone datasets analysis , 2015, EPJ Data Science.

[32]  Caroline O. Buckee,et al.  Digital Epidemiology , 2012, PLoS Comput. Biol..

[33]  Nathan Eagle,et al.  Parameterizing the Dynamics of Slums , 2010, AAAI Spring Symposium: Artificial Intelligence for Development.

[34]  Leo Breiman,et al.  Stacked regressions , 2004, Machine Learning.

[35]  Mirco Musolesi,et al.  Disease Containment Strategies based on Mobility and Information Dissemination , 2015, Scientific Reports.

[36]  Margaret Martonosi,et al.  ON CELLULAR , 2022 .

[37]  Erik Strumbelj,et al.  Explaining prediction models and individual predictions with feature contributions , 2014, Knowledge and Information Systems.

[38]  Ling Bian,et al.  Spatial Approaches to Modeling Dispersion of Communicable Diseases – A Review , 2013, Trans. GIS.

[39]  David L. Smith,et al.  Quantifying the Impact of Human Mobility on Malaria , 2012, Science.

[40]  Peter Piot,et al.  Joint United Nations Program on HIV/AIDS (UNAIDS) , 1997 .

[41]  Albert-László Barabási,et al.  Understanding individual human mobility patterns , 2008, Nature.

[42]  P. Olivier,et al.  Socio-Geography of Human Mobility: A Study Using Longitudinal Mobile Phone Data , 2012, PloS one.

[43]  Zbigniew Smoreda,et al.  On the Use of Human Mobility Proxies for Modeling Epidemics , 2013, PLoS Comput. Biol..

[44]  J. Larmarange,et al.  HIV estimates at second subnational level from national population-based surveys , 2014, AIDS.

[45]  T. Geisel,et al.  Natural human mobility patterns and spatial spread of infectious diseases , 2011, 1103.6224.

[46]  Elizabeth Marum,et al.  Shadow on the continent: public health and HIV/AIDS in Africa in the 21st century , 2002, The Lancet.

[47]  Gladys Mutangadura,et al.  The spread and effect of HIV-1 infection in sub-Saharan Africa , 2002, The Lancet.

[48]  T. Scott,et al.  Socially structured human movement shapes dengue transmission despite the diffusive effect of mosquito dispersal. , 2014, Epidemics.

[49]  César A. Hidalgo,et al.  Unique in the Crowd: The privacy bounds of human mobility , 2013, Scientific Reports.

[50]  Yu-Ru Lin,et al.  Mesoscopic Structure and Social Aspects of Human Mobility , 2012, PloS one.

[51]  W. Cumberland,et al.  Social Networking Technologies as an Emerging Tool for HIV Prevention , 2013, Annals of Internal Medicine.

[52]  Alberto Rubio,et al.  Measuring the impact of epidemic alerts on human mobility using cell-phone network data , 2011 .

[53]  Sally Blower,et al.  Using geospatial modeling to optimize the rollout of antiretroviral-based pre-exposure HIV interventions in Sub-Saharan Africa , 2014, Nature Communications.

[54]  Carlo Ratti,et al.  Transportation mode inference from anonymized and aggregated mobile phone call detail records , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[55]  Antonio Lima,et al.  Exploiting Cellular Data for Disease Containment and Information Campaigns Strategies in Country-Wide Epidemics , 2013, ArXiv.

[56]  Zbigniew Smoreda,et al.  D4D-Senegal: The Second Mobile Phone Data for Development Challenge , 2014, ArXiv.