Mobile Mental Health Screening in EmotiZen via the Novel Brain-Inspired MCoG-LDPSNet
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Anxiety and depression affect millions worldwide, yet stigma and long wait times often delay access to care. Mobile mental health apps can decrease these barriers by offering on-demand screening and support. Nevertheless, many machine and deep learning methods used in such tools perform poorly under severe class imbalance, yielding biased, poorly calibrated predictions. To address this challenge, this study proposes MCoG-LDPSNet, a brain-inspired model that combines dual, orthogonal encoding pathways with a novel Loss-Driven Parametric Swish (LDPS) activation. LDPS implements a neurobiologically motivated adaptive-gain mechanism via a learnable β parameter driven by calibration and confidence-aware loss signals that amplifies minority-class patterns while preserving overall reliability, enabling robust predictions under severe data imbalance. On a benchmark mental health corpus, MCoG-LDPSNet achieved AUROC = 0.9920 and G-mean = 0.9451, outperforming traditional baselines like GLMs, XGBoost, state-of-the-art deep models (CNN-BiLSTM-ATTN), and transformer-based approaches. After transfer learning to social media text, the MCoG-LDPSNet maintained a near-perfect AUROC of 0.9937. Integrated into the EmotiZen App with enhanced app features, MCoG-LDPSNet was associated with substantial symptom reductions (anxiety 28.2%; depression 42.1%). These findings indicate that MCoG-LDPSNet is an accurate, imbalance-aware solution suitable for scalable mobile screening of individuals for anxiety and depression.
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.
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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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 it