Comparing personalized brain-based and genetic risk scores for major depressive disorder in large population samples of adults and adolescents
Bibliographic record
Abstract
Abstract Background Major depressive disorder (MDD) is a polygenic disorder associated with brain alterations but until recently, there have been no brain-based metrics to quantify individual-level variation in brain morphology. Here, we evaluated and compared the performance of a new brain-based ‘Regional Vulnerability Index’ (RVI) with polygenic risk scores (PRS), in the context of MDD. We assessed associations with syndromal MDD in an adult sample ( N = 702, age = 59 ± 10) and with subclinical depressive symptoms in a longitudinal adolescent sample (baseline N = 3,825, age = 10 ± 1; 2-year follow-up N = 2,081, age = 12 ± 1). Methods MDD-RVIs quantify the correlation of the individual’s corresponding brain metric with the expected pattern for MDD derived in an independent sample. Using the same methodology across samples, subject-specific MDD-PRS and six MDD-RVIs based on different brain modalities (subcortical volume, cortical thickness, cortical surface area, mean diffusivity, fractional anisotropy, and multimodal) were computed. Results In adults, MDD-RVIs (based on white matter and multimodal measures) were more strongly associated with MDD ( β = 0.099–0.281, P FDR = 0.001–0.043) than MDD-PRS ( β = 0.056–0.152, P FDR = 0.140–0.140). In adolescents, depressive symptoms were associated with MDD-PRS at baseline and follow-up ( β = 0.084–0.086, p = 1.38 × 10 −4 −4.77 × 10 −4 ) but not with any MDD-RVIs ( β < 0.05, p > 0.05). Conclusions Our results potentially indicate the ability of brain-based risk scores to capture a broader range of risk exposures than genetic risk scores in adults and are also useful in helping us to understand the temporal origins of depression-related brain features. Longitudinal data, specific to the developmental period and on white matter measures, will be useful in informing risk for subsequent psychiatric illness.
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 | 0.001 |
| 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".