PT  - JOURNAL ARTICLE
AU  - Thin Nguyen
AU  - Truyen Tran
AU  - Wei Luo
AU  - Sunil Gupta
AU  - Santu Rana
AU  - Dinh Phung
AU  - Melanie Nichols
AU  - Lynne Millar
AU  - Svetha Venkatesh
AU  - Steve Allender
TI  - Web search activity data accurately predict population chronic disease risk in the USA
AID  - 10.1136/jech-2014-204523
DP  - 2015 Jul 01
TA  - Journal of Epidemiology and Community Health
PG  - 693--699
VI  - 69
IP  - 7
4099  - http://jech.bmj.com/content/69/7/693.short
4100  - http://jech.bmj.com/content/69/7/693.full
SO  - J Epidemiol Community Health2015 Jul 01; 69
AB  - Background The WHO framework for non-communicable disease (NCD) describes risks and outcomes comprising the majority of the global burden of disease. These factors are complex and interact at biological, behavioural, environmental and policy levels presenting challenges for population monitoring and intervention evaluation. This paper explores the utility of machine learning methods applied to population-level web search activity behaviour as a proxy for chronic disease risk factors.Methods Web activity output for each element of the WHO's Causes of NCD framework was used as a basis for identifying relevant web search activity from 2004 to 2013 for the USA. Multiple linear regression models with regularisation were used to generate predictive algorithms, mapping web search activity to Centers for Disease Control and Prevention (CDC) measured risk factor/disease prevalence. Predictions for subsequent target years not included in the model derivation were tested against CDC data from population surveys using Pearson correlation and Spearman's r.Results For 2011 and 2012, predicted prevalence was very strongly correlated with measured risk data ranging from fruits and vegetables consumed (r=0.81; 95% CI 0.68 to 0.89) to alcohol consumption (r=0.96; 95% CI 0.93 to 0.98). Mean difference between predicted and measured differences by State ranged from 0.03 to 2.16. Spearman's r for state-wise predicted versus measured prevalence varied from 0.82 to 0.93.Conclusions The high predictive validity of web search activity for NCD risk has potential to provide real-time information on population risk during policy implementation and other population-level NCD prevention efforts.