JMIR Publications

ABSTRACT

Background:

While a plethora of weight management apps are available mostly for dietary self-monitoring, many individuals especially those with overweight and obesity still struggle to achieve adequate weight loss. An emerging area in weight management is the support for one’s self-regulation over momentary eating impulses.

Objective:

To examine the feasibility and effectiveness of a novel artificial intelligence (AI)-assisted weight management app on improving eating behaviors.

Methods:

A single group, pretest posttest study was conducted. Participants completed the one-week run-in of a 12-weeks app-based weight management program called the Eating Trigger-Response Inhibition Program (eTRIP). The self-monitoring system was built upon three main components namely (1) chatbot-based check-ins on eating lapse triggers, (2) food-based computer vision image recognition (system built based on local food items), and (3) automated time-based nudges and meal stopwatch. At every mealtime, participants were prompted to take a picture of their food, of which the food items were identified by a computer vision image recognition technology, which then triggered a set of chatbot-initiated questions on eating triggers such as who the users were eating with. Paired t-tests were used to compare the differences in psycho-behavioral constructs before and after the 7 days program, including overeating habit, snacking habit, consideration of future consequences, self-regulation of eating behaviors, anxiety, depression, and physical activity. Qualitative feedbacks were analyzed using content analysis according to the four steps namely decontextualization, recontextualization, categorization and compilation.

Results:

The mean age, and self-reported BMI and waist circumference was 31.25 ± 9.98 years, 28.86 ± 7.02 kg/m2, and 92.58 ± 18.23 cm respectively. There were significant improvements in all the seven psycho-behavioral constructs except for anxiety. After adjusting for multiple comparisons, statistically significant improvements were found for overeating habit (-0.32 ±1.16, P<.001), snacking habit (-0.22 ± 1.12, P<.002), self-regulation of eating behavior (0.08 ± 0.49, P=.007), depression (-0.12 ± 0.74, P=.007), and physical activity (1288.60 ± 3055.20 MET-min/day, P<.001). Forty-one participants reported skipping at least 1 meal (i.e. breakfast, lunch or dinner), summing to a total of 578 (67.1%) of meals skipped. Eighty (34.8%) participants provided textual feedback that indicated a satisfactory user experience from using the eTRIP. Four themes emerged namely (1) becoming more mindful with self-monitoring; (2) personalized reminders with prompts and chatbot; (3) food logging with image recognition; and (4) engaging with simple, easy, and appealing user interface. Attrition rate was 8.7%.

Conclusions:

eTRIP is a feasible and effective weight management program to be tested in a larger population for its effectiveness and sustainability as a personalized weight management program from people with overweight and obesity. Clinical Trial: ClinicalTrials.gov (ref. NCT04833803) registered on the 6th April 2021.