Document Type
Article
Keywords
applied computing; computing methodologies; law, social and behavioral sciences; psychology; machine learning; learning paradigms; supervised learning; human centered computing
Identifier Data
https://doi.org/10.1145/3643554
Publisher
Association for Computing Machinery
Rights Management
© 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.
Abstract
Major Depressive Disorder (MDD) and Generalized Anxiety Disorder (GAD) are both heterogeneous in their clinical presentations, manifesting with unique symptom profiles. Despite this, prior digital phenotype research has primarily focused on disorder-level detection rather than symptom-level detection. In this research, we predict the existence of individual symptoms of MDD and GAD with SMS log metadata, and ensemble these symptom-level classifiers to screen for depression and anxiety, thus accounting for disorder heterogeneity. Further, we collect an additional dataset of retrospectively harvested SMS logs to augment an existing dataset collected after COVID-19 altered communication patterns, and propose two new types of distribution features: consecutive messages and conversation ratio. Our symptom-level detectors achieved a balanced accuracy of 0.7 in 13 of the 16 MDD and GAD symptoms, with reply latency distribution features achieving a balanced accuracy of 0.78 when detecting anxiety symptom trouble relaxing. When combined into disorder-level ensembles, these symptom-level detectors achieved a balanced accuracy of 0.76 for depression screening and 0.73 for anxiety screening, with tree boosting methods demonstrating particular efficacy. Accounting for disorder heterogeneity, our research provides insight into the value of SMS logs for the assessment of depression and anxiety diagnostic criteria.
Included in
Business Analytics Commons, Databases and Information Systems Commons, Data Science Commons, Management Information Systems Commons
