Voice Recordings from Short Mobile Sessions versus Clinical Interviews for Mental Illness Screening: A Comparative Study with Deep Transfer Learning
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/10.1109/TAFFC.2025.3568385
Publisher
Association for Computing Machinery
Rights Management
CC-BY-NC
Abstract
The prevalence of mental illness symptoms is increasing. While questionnaires are traditionally used, prior research applied machine learning to clinical interview recordings conducted by a virtual agent for depression screening. In this research, we compare their screening ability with brief mobile voice recordings. The latter reduces completion time while increasing access to screening. We collected 546 mobile voice recordings in response to four clinical interview questions from over 200 crowd-sourced adults reporting English fluency. We also collected responses to traditional screening questionnaires to use as labels in the classifiers. We extract textual transcripts from these voice recordings, facilitating both unimodal and multimodal classification. We compose acoustic and language representation models into deep learning architectures fine-tuned for mental illness screening. In our study, we compare the mental illness screening ability of four questions from mobile voice recordings and complete clinical interviews. When screening for depression, the brief mobile voice responses to individual questions proved as good or better for half of the interview questions. Overall, we achieved AUC of 0.76 for depression, 0.76 for anxiety, and 0.81 for suicidal ideation screening using our mobile voice recordings. Our findings can help guide the development of efficient and effective mental illness screening technologies.
