Detection of Depressive Symptoms in College Students Using Multimodal Passive Sensing Data and Light Gradient Boosting Machine: Longitudinal Pilot Study
Bibliographic record
Abstract
BACKGROUND: Depression is the top contributor to global disability. Early detection of depression and depressive symptoms enables timely intervention and reduces their physical and social consequences. Prevalence estimates of depression approach 30% among college students. Passive, device-based sensing further enables detection of depressive symptoms at a low burden to the individual. OBJECTIVE: We leveraged an ensemble machine learning method (light gradient boosting machine) to detect depressive symptoms entirely through passive sensing. METHODS: A diverse sample of undergraduate students (N=28; mean age 19.96, SD 1.23 y; 15/28, 54% women; 13/28, 46% Latine; 10/28, 36% Asian; 4/28, 14% non-Latine White; 11/28, 4% other) participated in an intensive longitudinal study. Participants wore 2 devices (an Oura ring for sleep and physiology data, and a Samsung smartwatch for physiology and movement data) and installed the AWARE software on their mobile devices, which collects passive sensing data such as screen time. Participants were derived from a randomized controlled trial of a positive psychology mobile health intervention. They completed a self-report measure of depressive symptoms administered weekly over a 19- to 22-week period. RESULTS: -score of 0.744 and a Cohen κ coefficient of 0.474, indicating moderate agreement between the predicted labels and the ground truth. The most predictive features of depressive symptoms were sleep quality and missed mobile interactions. CONCLUSIONS: Findings suggest that data collected from passive sensing devices may provide real-time, low-cost insight into the detection of depressive symptoms in college students and may present an opportunity for future prevention and perhaps intervention.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".