Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Apr 5, 2021
Date Accepted: Feb 17, 2022
Date Submitted to PubMed: Apr 18, 2022
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Weight loss trajectories and related factors in a 16-week mobile obesity intervention: A retrospective observational study
ABSTRACT
Background:
In obesity management, whether patients lose 5% or more of their initial weight is a critical factor in their clinical outcome. However, evaluations that only take this approach cannot identify and distinguish between individuals whose weight change varies and those who steadily lose weight. Evaluation of weight loss considering the volatility of weight change through a mobile-based intervention for obesity can facilitate the understanding of individuals’ behavior and weight changes from a longitudinal perspective.
Objective:
With machine learning approach, we examined weight loss trajectories and explored the factors related to behavioral and app usage characteristics that induce weight loss.
Methods:
We used the lifelog data of 19,784 individuals who enrolled in a 16-week obesity management program on the healthcare app Noom in the US during August 8, 2013 to August 8, 2019. We performed K-means clustering with dynamic time warping to cluster the weight loss time series and inspected the quality of clusters with the total sum of distance within the clusters. To identify the usage factors to determine clustering assignment, we longitudinally compared weekly usage statistics with effect size on a weekly basis.
Results:
Initial Body Mass Index (BMI) of participants was 33.9±5.9 kg/m2, and ultimately reached an average BMI of 32.0±5.7 kg/m2. In their weight log, 5 Clusters were identified: Cluster 1 (sharp decrease) showed a high proportion of weight reduction class between 10% and 15%—the highest among the five clusters (n=2,364/12,796, 18.9%)—followed by Cluster 2 (moderate decrease), Cluster 3 (increase), Cluster 4 (yoyo), Cluster 5 (other). In comparison between cluster 2 and cluster 4, although the effect size of difference in the average meal input adherence and average weight input adherence did not show a significant difference in the first week, it increased continuously for 7 weeks (Cohen’s d=0.408; 0.38).
Conclusions:
With machine learning approach clustering shape-based timeseries similarity, this study identified 5 weight loss trajectories in mobile weight management app. Overall adherence and early adherence related to self-monitoring emerged as a potential predictor of these trajectories.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.