Using demographics to predict smartphone health app adoption and intentions to improve wellbeing

Background: Smartphone use and the adoption of healthy lifestyle software applications (“health apps”) are rapidly proliferating. There is limited information on users of the health apps in terms of their characteristics, intentions to change, and actual health behaviours. The study objectives were to 1) to describe the socio-demographic and health behaviour characteristics associated with health app use in a recent U.S. nationally representative sample; 2) to assess the predictors of use of health apps for health promotion, and 3) to examine the association between use of health-related apps and meeting the recommended guidelines for fruit and vegetable intake and physical activity.Methods: Data on 3,677 users of mobile devices and health apps were analysed from National Cancer Institute’s 2015 Health Information National Trends Survey (HINTS), designed to provide nationally representative estimates for health information in the US and is publicly available online. Machine learning evaluation and multivariable logistic regression models were used to assess socio-demographic predictors of mobile device and health app use and examine associations between app use, intentions to change behaviour, and actual behaviour change for fruit and vegetable consumption, physical activity, and weight loss.Findings: Older individuals (45 to 64 years, OR=0.56; 65+ years, OR=0.19), males (OR=0.80), and having a degree (OR=2.83) or less than high school education (OR=0.43) were all significantly associated with a reduced likelihood of having adopted mobile technology; these variables were mildly to moderately potent in predicting mobile technology adoption. Individuals with apps were significantly more likely to report intentions to improve fruit (P=0.01) and vegetable (P