Improving Depression Assessment With Multi-Task Learning From Speech and Text Information
Bibliographic record
Abstract
Early recognition and treatment of depression can avert escalation of the mental disorder and alleviate suffering for the patients and their families. Automated depression screening tools have been proposed to complement existing clinical methods for rapid intervention. Beyond the traditional objectives of detecting depression and estimating its severity, we propose a novel multi-task deep learning framework to improve an automated depression assessment task by additionally estimating depression-related symptom severities. Experiments carried out on the Distress Analysis Interview Corpus showed that the joint predictions of depression assessment outcomes improve both prediction performances and probability calibration. For high-stakes applications such as medical diagnosis, probability calibration of machine learning models is critical for avoiding decisions made with over- or under-confidence, both of which could result in severe consequences. In addition, the estimated symptom severities can serve to provide clinicians with explanations for the overall prediction, a useful feature for clinical practice. Using both speech and textual features extracted from the clinical interviews, our method also achieved competitive results against state-of-the-art models.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".