Digital Phenotyping Self-Monitoring Behaviors for Individuals With Type 2 Diabetes Mellitus: Observational Study Using Latent Class Growth Analysis

Abstract

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Sustained self-monitoring and self-management behaviors are crucial to maintain optimal health for individuals with type 2 diabetes mellitus (T2DM). As smart phones and mobile health (mHealth) devices become widely available, self-monitoring by using mHealth devices is becoming an appealing strategy in support of successful self-management. However, research indicates that engagement with mHealth devices decreases over time. Thus, it’s important to understand engagement trajectories in order to provide varying levels of support to improve self-monitoring and self-management behaviors. Objective: The purposes of this study were to develop (1) digital phenotypes of T2DM individual’s self-monitoring behaviors based on their engagement trajectory of using multiple mHealth devices, and (2) assess the association of individual digital phenotypes of self-monitoring behaviors with baseline demographic and clinical characteristics. Methods: This longitudinal observational feasibility study included participants (N=60) with T2DM instructed to monitor weight, blood glucose, and physical activity by using a wireless weight scale, phone-tethered glucometer, and accelerometer, respectively, over six months. We used a latent class growth analysis (LCGA) with multi-trajectory modeling to digital phenotype participants’ self-monitoring behaviors based on their engagement trajectories with multiple mHealth devices. Associations between individual characteristics and digital phenotypes on participants’ self-monitoring behavior were assessed by ANOVA or Chi-square tests. Results: The engagement with accelerometers to monitor daily physical activities were consistently high for all participants over time. There were three distinct digital phenotypes identified based on participants’ engagement with the wireless weight scale and glucometer: (1) low and waning engagement group (N=24); (2) medium engagement group (N=20); and (3) consistently high engagement group (N=16). Participants that were younger, female, non-white, low income and with higher baseline HbA1c were more likely to be in low and waning engagement group. Conclusions: We demonstrated digital phenotyping individuals’ self-monitoring behavior based on their engagement trajectory with multiple mobile health devices. Distinct self-monitoring behavior groups were observed. Individual demographic and clinical characteristics were associated with different self-monitoring behavior groups. Future research should identify methods to provide tailored support for people with T2DM so they can better monitor and manage their condition.