Examining engagement amongst mobile health app users: a 6-month latent class analysis study

BACKGROUND: Mobile health application (mHealth app) effectiveness may be limited by low engagement. Increasing understanding of factors influencing engagement may help. mHealth app subscription and renewal are two metrics of interest to commercial app publishers. PURPOSE: To identify homogenous user subgroups (i.e., behavioural phenotypes) within a paid mHealth app context and examine associations with subscription and renewal. METHODS: A 6-month latent class analysis (LCA) study was conducted with new users of the WayBetter app, a subscription-based mHealth app with financial incentives. Users completing a 7-day free trial between November 2, 2023 and January 3, 2024 were included. LCA produced phenotypes using (1) purpose-built survey responses (e.g., socio-demographics, previous health behaviours, personality traits), (2) device-assessed health data (e.g., daily step count), and (3) 7-day trial period engagement data (e.g., number of app opens). Odds ratios (OR; pRESULTS: The total sample included 934 users (2[SD]=42.00 [9.65] years; % women= 91.10%). Based on key LCA fit indices (e.g., Vuong-Lo-Mendell-Rubin likelihood test=467.16, p=0.032), and theoretical interpretability, five distinct phenotypes were formed: (1) Highly Engaged Subscribers, (2) Subscribers with Multimorbidity, (3) Healthy Subscribers, (4) Non-subscribers with Multimorbidity, and (5) Healthy Non-Subscribers. Phenotypes 1, 2, and 3 had greater odds of subscribing (OR= 21.31, [8.56,53.06]; OR=7.11, [4.04,12.50]; OR=8.28, [4.26,16.08], respectively) than phenotype 4 (OR=0.82, [0.48,1.41]), compared to phenotype 5, the reference. As well, the odds phenotypes 1, 2, 3 and 4 renewed were OR=1.06, [0.62,1.81]; OR=0.900, [0.54,1.49]; OR=0.99, [1.0,1.8], OR=0.5, [0.3,0.7], respectively (compared to the reference class phenotype 5). CONCLUSION: Behavioural phenotypes likely or not to subscribe were identified using data collected during the 7-day free trial period. These may be targeted with future intervention.