Developing and validating a prediction model of adolescent major depressive disorder in the offspring of depressed parents
Bibliographic record
Abstract
BACKGROUND: Parental depression is common and is a major risk factor for depression in adolescents. Early identification of adolescents at elevated risk of developing major depressive disorder (MDD) in this group could improve early access to preventive interventions. METHODS: Using longitudinal data from 337 adolescents at high familial risk of depression, we developed a risk prediction model for adolescent MDD. The model was externally validated in an independent cohort of 1,384 adolescents at high familial risk. We assessed predictors at baseline and MDD at follow-up (a median of 2-3 years later). We compared the risk prediction model to a simple comparison model based on screening for depressive symptoms. Decision curve analysis was used to identify which model-predicted risk score thresholds were associated with the greatest clinical benefit. RESULTS: The MDD risk prediction model discriminated between those adolescents who did and did not develop MDD in the development (C-statistic = .783, IQR (interquartile range) = .779, .778) and the validation samples (C-statistic = .722, IQR = -.694, .741). Calibration in the validation sample was good to excellent (calibration intercept = .011, C-slope = .851). The MDD risk prediction model was superior to the simple comparison model where discrimination was no better than chance (C-statistic = .544, IQR = .536, .572). Decision curve analysis found that the highest clinical utility was at the lowest risk score thresholds (0.01-0.05). CONCLUSIONS: The developed risk prediction model successfully discriminated adolescents who developed MDD from those who did not. In practice, this model could be further developed with user involvement into a tool to target individuals for low-intensity, selective preventive 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 | 0.009 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 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".