Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Jul 26, 2023
Date Accepted: Jul 24, 2024
Digital phenotypes of mobile keyboard backspace rates and relations to symptoms of mood disorder: a Bayesian Mixture Model
ABSTRACT
Background:
Passive sensing through smartphone keyboard data has shown promise in identifying and monitoring symptoms of mood disorders with low participant burden. This approach involves behavioral phenotyping based on the analysis of smartphone keyboard data, which can potentially aid in clinical decision-making and provide insights into individual symptoms of mood disorders.
Objective:
The objective of the current study was to derive digital phenotypes from smartphone keyboard backspace use to better understand mood disorders. The study aimed to explore correlations between these derived phenotypes and mood disorder diagnoses, severity, and individual symptoms of depression and mania.
Methods:
The study involved 128 community adults, and data were collected across 2948 observations. We employed a Bayesian mixture model to derive digital phenotypes from smartphone keyboard backspace use. We then examined the relations between derived phenotype and mood disorder diagnoses and symptoms.
Results:
The derived digital phenotypes demonstrated significant correlations with mood disorder diagnoses, severity levels, and individual symptoms of depression and mania.
Conclusions:
The study highlighted the potential of digital phenotyping based on smartphone keyboard data as an ecologically valid and data-driven approach for diagnosing mood disorders. The findings indicated that this method could offer valuable insights for clinicians, researchers, and administrators in the field of mental health. By utilizing mobile kinetics, clinicians can make more informed decisions about diagnosis, treatment, and resource allocation, leading to better outcomes for individuals with mood disorders.
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.