JMIR Publications

ABSTRACT

Background:

The prevalence of chronic conditions such as obesity, hypertension, and diabetes are increasing in African countries. Behavioral risk factor data usually obtained from surveys can be delayed by years. Behavioral data from digital sources can be used in the timely monitoring of behavioral risk factors.

Objective:

The objective of our study is to propose the use of digital data and technology for monitoring changes in behavioral risk factors.

Methods:

We obtained the adjusted volume of search queries submitted to Google for 108 diet, exercise and disease-related terms from 2010 to 2016. We also obtained obesity and overweight prevalence for 52 African countries from the World Health Organization (WHO) for the same period. Machine learning algorithms (i.e. random forest, support vector machines, Bayes GLM, gradient boosting and an ensemble of the individual methods) were used to identify search terms and patterns that correlate with changes in obesity and overweight prevalence across Africa. Out-of-sample predictions were used to assess and validate the model performance

Results:

The study included 52 African countries. In 2016, the WHO reported overweight prevalence ranged from 20.9 (95% CI, 17.1-25.0) to 66.8 (95% CI, 62.4-71.0) and obesity prevalence ranged from 4.5 (95% CI, 2.9-6.5) to 32.5 (95% CI, 27.2-38.1) in Africa. The highest obesity and overweight prevalence were noted in the northern and southern regions. Searches for diet, exercise and obesity-related terms explained 97.3 % (root mean squared error [RMSE] 1.15) variation in obesity prevalence across all 52 countries. Similarly, the search data explained 96.6% (RMSE 2.26) variation in overweight prevalence. The search terms yoga, exercise and gym were most correlated with changes in obesity and overweight prevalence in countries with the highest prevalence.

Conclusions:

Information seeking patterns for diet and exercise related terms could indicate changes in attitudes towards and engagement in risk factors or healthy behaviors. These trends could capture population changes in risk factor prevalence, can inform digital and physical interventions and supplement official data from surveys.