Digital Voice Journaling for Depressive Symptoms in Youth: Predicting Symptom Changes Using Machine Learning.
- 1Li Chiu Kong Family Sleep Assessment Unit, Department of Psychiatry, The Chinese University of Hong Kong, Hong Kong SAR, China.
- 2Li Ka Shing Institute of Health Sciences, Faculty of Medicine, The Chinese University of Hong Kong, Hong Kong SAR, China.
- 3Gerald Choa Neuroscience Institute, The Chinese University of Hong Kong, Hong Kong SAR, China.
Abstract
Background/objectives
Given the existing evidence supporting the benefits of journaling, digital voice journaling may represent a promising approach for alleviating depressive symptoms. This study examined changes in depressive symptoms associated with its use, identified linguistic and acoustic correlates of symptom improvement, and developed machine learning models to predict subsequent improvement.Methods
The study employed a pretest-posttest design. Young adults aged 18-24 years with depressive symptoms (17-item Hamilton Depression Rating Scale [HAMD-17] ≥ 8) completed a seven-day digital voice journaling with twice-daily prompts, followed by a repeated HAMD-17 assessment. Linguistic and acoustic features extracted from the recordings were used to develop 12 machine learning models through five-fold cross-validation, for predicting symptom remission (post-journaling HAMD-17 < 8) and improvement (reduction in severity category), and model performance is evaluated using pooled AUC.Results
Among the 68 participants (age = 20.78 ± 1.98 years; 85.29% female), a mean decrease of 4.54 points in HAMD-17 scores was found with a moderate effect size (Cohen's d = 0.78). Improvement and remission were observed in 61.76% (n = 42) and 52.94% (n = 36) of participants, respectively. Multiple linguistic and acoustic features, including achievement-related words, function words, F2 formant frequency, and MFCC 2, were significantly associated with these outcomes. The highest-performing models achieved AUCs of 0.86 (95% CI: 0.76-0.94) for improvement and 0.88 (95% CI: 0.79-0.95) for remission.Conclusions
Depressive symptoms decreased during the seven-day voice journaling period, although the uncontrolled design limits causal interpretation of this change. Furthermore, linguistic and acoustic features may help identify individuals who are more likely to experience symptom improvement or remission.
Related
- Social Capital, Life Meaning, and Depressive Symptoms Among Older Adults in China: The Moderating Roles of Digital Social Participation and Digital Social Interaction
- Disaggregating Digital Competence: Social Activity Participation and Depressive Symptoms Among Korean Older Adults
- Low Digital Engagement, Depressive Symptoms, and Probable Cognitive Impairment Among Community-Dwelling Older Adults in Shanghai: A Cross-Sectional Path Analysis of Self-Perceived Burden, Uselessness, and Loneliness
- Predicting Depressive Symptoms From Cross-Sectional and Longitudinal Data Using XGBoost-SHAP and Cross-Lagged Model.
- Machine learning-based risk screening model for depressive symptoms in middle-aged and elderly cardiovascular disease patients
BibTeX
@article{ku2026digital,
title = {{Digital Voice Journaling for Depressive Symptoms in Youth: Predicting Symptom Changes Using Machine Learning.}},
author = {Dorothy Ka Ki Ku and Alyssa Yuet Chin Wong and Kit Ying Chan and Yun Kwok Wing and Tim Man Ho Li},
journal = {Healthcare (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/healthcare14193238},
url = {https://europepmc.org/article/MED/42881676},
note = {CC BY},
}
RIS
TY - JOUR
TI - Digital Voice Journaling for Depressive Symptoms in Youth: Predicting Symptom Changes Using Machine Learning.
AU - Dorothy Ka Ki Ku
AU - Alyssa Yuet Chin Wong
AU - Kit Ying Chan
AU - Yun Kwok Wing
AU - Tim Man Ho Li
PY - 2026
DA - 2026/10/01
JO - Healthcare (Basel, Switzerland)
DO - 10.3390/healthcare14193238
UR - https://europepmc.org/article/MED/42881676
AB - Background/objectives Given the existing evidence supporting the benefits of journaling, digital voice journaling may represent a promising approach for alleviating depressive symptoms. This study examined changes in depressive symptoms associated with its use, identified linguistic and acoustic correlates of symptom improvement, and developed machine learning models to predict subsequent improvement.Methods The study employed a pretest-posttest design. Young adults aged 18-24 years with depressive symptoms (17-item Hamilton Depression Rating Scale [HAMD-17] ≥ 8) completed a seven-day digital voice journaling with twice-daily prompts, followed by a repeated HAMD-17 assessment. Linguistic and acoustic features extracted from the recordings were used to develop 12 machine learning models through five-fold cross-validation, for predicting symptom remission (post-journaling HAMD-17 < 8) and improvement (reduction in severity category), and model performance is evaluated using pooled AUC.Results Among the 68 participants (age = 20.78 ± 1.98 years; 85.29% female), a mean decrease of 4.54 points in HAMD-17 scores was found with a moderate effect size (Cohen's d = 0.78). Improvement and remission were observed in 61.76% (n = 42) and 52.94% (n = 36) of participants, respectively. Multiple linguistic and acoustic features, including achievement-related words, function words, F2 formant frequency, and MFCC 2, were significantly associated with these outcomes. The highest-performing models achieved AUCs of 0.86 (95% CI: 0.76-0.94) for improvement and 0.88 (95% CI: 0.79-0.95) for remission.Conclusions Depressive symptoms decreased during the seven-day voice journaling period, although the uncontrolled design limits causal interpretation of this change. Furthermore, linguistic and acoustic features may help identify individuals who are more likely to experience symptom improvement or remission.
SN - 2227-9032
ER -