JMIR Publications

ABSTRACT

Background:

Early weight loss is an established predictor for treatment outcomes in weight management interventions for people with obesity. However, there is a paucity of additional, reliable, and clinically actionable early predictors in weight management interventions. Novel blended-care weight management interventions combine coach- and app-support and afford new means of structured, continuous data collection, informing research on treatment adherence and outcome prediction.

Objective:

Against this backdrop, this study analyzes app engagement as a predictor for weight loss in large-scale, real-world, blended-care interventions. Patients who engaged higher in app usage in blended-care treatment (i. e., higher logging activity) lose more weight than patients who engage comparably lower at three and six months of intervention.

Methods:

Real-world data from 19260 patients in obesity treatment were analyzed retrospectively. Patients were treated in three different blended-care weight management interventions, offered in Switzerland (CH), the United Kingdom (UK), and Germany (DE) by a digital behavior change provider. Principal component analysis identified an over-arching metric for app engagement based on app usage. A median split informed a distinction in higher and lower engagers among the patients. Both groups were matched via optimal propensity score matching for relevant characteristics (e.g., gender, age, start weight). A linear regression model, combining patient characteristics and app-derived data, was applied to identify predictors for weight loss outcomes.

Results:

Across countries, higher app engagement yielded more weight loss than lower engagement after three but not after six months of intervention (P(3 months) < .001, P(6 months = .95). Early app engagement within the first 3 months predicted percentage weight loss in all countries, respectively (P(CH) < .001, P(UK) = .04, P(DE)= .007). Higher age was associated with stronger weight loss in the three months period (P(CH) = .003, P(UK) = .001, P(DE) < .001) but not in the six months period (P(CH) = .25, P(UK) = .63, P(DE) = .13). In Switzerland, higher numbers of patients’ messages to coaches was associated with higher weight loss (P(3 months) < .001, P(6 months) < .001). Messages from coaches were not significantly associated with weight loss.

Conclusions:

Early app engagement is a predictor of weight loss - with higher engagement yielding more weight loss than lower engagement in this analysis. This new predictor lends itself to automated monitoring and as a digital indicator for needed or adapted clinical action. Further research needs to establish the reliability of early app engagement as a predictor for treatment adherence and outcomes. In general, the obtained results testify to the potential of app-derived data to inform clinical monitoring practices and intervention design.