JMIR Publications

ABSTRACT

Background:

Behavioral intervention remains an evidence-based treatment for obesity. However, structured cognitive behavioral therapy requires a long duration and frequent sessions, which burdens therapists and participants. We hypothesized that a smartphone application using reinforcement learning would effectively support this treatment.

Objective:

This study aimed to develop and evaluate the feasibility of such an application in individuals with obesity.

Methods:

We developed a smartphone application to assist in setting and reviewing daily behaviors related to weight loss. On the screen on which daily behaviors were shown, the order of presentation was optimized using Thompson sampling, a multi-armed bandit algorithm. Twenty individuals with obesity used the application for 4 weeks, and the daily app usage rates were quantified. Body weight and mood status were measured daily during the study, and the brief-type self-administered diet history questionnaire and the International Physical Activity Questionnaire were administered at the beginning and end of the study. The statistical significance of the changes in these measures was evaluated using the Wilcoxon signed-rank test. Furthermore, the longitudinal data collected during this study were analyzed using a linear mixed-effects model to examine factors related to the number of behaviors performed daily.

Results:

All 20 recruited individuals with obesity completed the 4-week study schedule. The median application usage rate was 98.3%. Significant improvements were observed in body mass index (median at start: 34.9 kg/m2, median at end: 34.1 kg/m2, P = 0.011), as well as daily energy intake and weekend sitting time. The linear mixed-effects model showed a significant association between higher preceding depressive mood levels and fewer behaviors.

Conclusions:

The feasibility of the smartphone application using reinforcement learning for obesity was sufficient, and the potential effectiveness of the treatment was suggested. Preceding depressive mood may influence daily behaviors related to weight loss. Clinical Trial: UMIN (ID: UMIN000048667)