Influence of Baseline User Characteristics and Early Use Patterns (24-Hour) on Long-Term Adherence and Effectiveness of a Web-Based Weight Loss Randomized Controlled Trial: Latent Profile Analysis

Background: Low adherence to real-world online weight loss interventions reduces long-term efficacy. Baseline characteristics and use patterns are determinants of long-term adherence, but we lack cohesive models to guide how to adapt interventions to users' needs. We also lack information whether very early use patterns (24 hours) help describe users and predict interventions they would benefit from. Objective: We aim to understand the impact of users' baseline characteristics and early (initial 24 hours) use patterns of a web platform for weight loss on user adherence and weight loss in the long term (24 weeks). Methods: We analyzed data from the POEmaS randomized controlled trial, a study that compared the effectiveness of a weight loss platform with or without coaching and a control approach. Data included baseline behavior and use logs from the initial 24 hours after platform access. Latent profile analysis (LPA) was used to identify classes, and Kruskal-Wallis was used to test whether class membership was associated with long-term (24 weeks) adherence and weight loss. Results: Among 828 participants assigned to intervention arms, 3 classes were identified through LPA: class 1 (better baseline health habits and high 24-hour platform use); class 2 (better than average health habits, but low 24-hour platform use); class 3 (worse baseline health habits and low 24-hour platform use). Class membership was associated with long-term adherence (P<.001), and class 3 members had the lowest adherence. Weight loss was not associated with class membership (P=.49), regardless of the intervention arm (platform only or platform + coach). However, class 2 users assigned to platform + coach lost more weight than those assigned to platform only (P=.02). Conclusions: Baseline questionnaires and use data from the first 24 hours after log-in allowed distinguishing classes, which were associated with long-term adherence. This suggests that this classification might be a useful guide to improve adherence and assign interventions to individual users.