Machine-learning analysis identifies digital behavioral phenotypes for engagement and health outcome efficacy of mHealth interventions for obesity: post-hoc analyses of a randomized trial

*Kim, M., *Yang, J., Ahn, W.-Y., & Choi, H. 2021. JMIR Preprint

Abstract

Background: The digital healthcare community has been urged to enhance engagement and clinical outcomes by analyzing multidimensional digital phenotypes.

Objective: This study aimed to investigate the performance of multivariate phenotypes predicting the engagement rate and health outcomes of digital cognitive behavioral therapy (dCBT) using a machine learning approach.

Methods: We leveraged both conventional phenotypes assessed by validated psychological questionnaires and multidimensional digital phenotypes within time-series data from a mobile app of 45 participants undergoing digital cognitive behavioral therapy (dCBT) for eight weeks. To discriminate the important characteristics, we conducted a machine-learning analysis.

Results: A higher engagement rate was associated with higher weight loss at 8 weeks (r = -0.59, p < 0001) and 24 weeks (r = -0.52, p = 0001). The machine learning approach revealed distinct multivariate profiles associated with varying impacts on the outcomes. Lower self-esteem on the conventional phenotype and higher in-app motivational measures on digital phenotypes commonly accounted for both engagement and health outcomes. In addition, eight types of digital phenotypes predicted engagement rates (mean R2 = 0416, SD = 0006). The prediction of short-term weight change (mean R2 = 0382, SD = 0015) was associated with six different digital phenotypes. Lastly, two behavioral measures of digital phenotypes were associated with a long-term weight change (mean R2 = 0590, SD = 0011).

Conclusions: Our findings successfully demonstrated how multiple psychological constructs, such as emotional, cognitive, behavioral, and motivational phenotypes, elucidate the mechanisms and clinical efficacy of digital intervention with the machine learning method. Our results also highlight the importance of assessing multiple aspects of motivation before and during the intervention to improve both engagement rate and clinical outcomes. This line of research may shed light on the development of advanced prevention and personalized digital therapeutics. Clinical Trial: ClinicalTrials.gov NCT03465306 (Retrieved September 18, 2017, https://register.clinicaltrials.gov/NCT03465306)