Warning: This is an author submission that is not peer-reviewed or edited.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.
Predicting Adherence to Behavior Change Support Systems using Machine Learning: A Systematic Review
ABSTRACT
Background:
The long-term effectiveness of behavior change support systems is currently hindered by non-adherence. Yet, there is a dearth of knowledge on reliable adherence prediction measures and predictors in behavior change support systems. Existing reviews have predominately focused on self-reporting measures of adherence to pharmacological and non-pharmacological interventions; these measures are susceptible to over or underestimation of adherence behavior.
Objective:
This review seeks to identify and summarize trends in the use of machine learning approaches to predict adherence to behavior change support systems.
Methods:
Systematic literature searches were conducted in the Scopus and PubMed electronic databases between January 2011 and August 2022. The initial search retrieved 2182 journal articles. After following predefined exclusion criteria, 11 of these articles were identified and selected to be relevant for the review.
Results:
Four main categories of adherence domains were identified in this review. These are physical activity adherence, diet adherence, medication adherence, lifestyle digital interventions adherence, and cognitive behavioral therapy adherence. The study also found that the use of machine learning techniques for real-time adherence prediction in behavior change support systems is gaining research attention. Thirteen unique supervised learning techniques were identified and the majority of them were traditional machine learning techniques (e.g., support vector machine). Long short-term memory, multilayer perception, and ensemble learning are currently the only advanced learning techniques. Despite the heterogeneity in the feature selection approaches, it was observed that most prediction models have good classification accuracies. This indicates that the features/predictors used in each of the included studies were a good representation of the adherence problem.
Conclusions:
The use of machine learning algorithms in predicting the adherence behavior of behavior change support systems users will facilitate the reinforcement of adherence behavior by providing more personalized and timely suggestions to users. Relevant implications for practice include considering identified predictors and machine learning techniques in future related studies to enable a comparison of evidence-based results.
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.