Parsing the heterogeneity of depression: a data-driven subgroup derived from cognitive function
Bibliographic record
Abstract
Background: Increasing evidences suggests that depression is a heterogeneous clinical syndrome. Cognitive deficits in depression are associated with poor psychosocial functioning and worse response to conventional antidepressants. However, a consistent profile of neurocognitive abnormalities in depression remains unclear. Objective: We used data-driven parsing of cognitive performance to reveal subgroups present across depressed individuals and then investigate the change pattern of cognitive subgroups across the course in follow-up. Method: We assessed cognition in 163 patients with depression using The Chinese Brief Cognitive Test(C-BCT) and the scores were compared with those of 196 healthy controls (HCs). 58 patients were reassessed after 8 weeks. We used K-means cluster analysis to identify cognitive subgroups, and compared clinical variables among these subgroups. A linear mixed-effects model, incorporating time and group (with interaction term: time × group) as fixed effects, was used to assess cognitive changes over time. Stepwise logistic regression analysis was conducted to identify risk factors associated with these subgroups. Results: Two distinct neurocognitive subgroups were identified: (1) a cognitive-impaired subgroup with global impairment across all domains assessed by the C-BCT, and (2) a cognitive-preserved subgroup, exhibited intact cognitive function, with performance well within the healthy range. The cognitive-impaired subgroup presented with more severe baseline symptoms, including depressed mood, guilt, suicidality, and poorer work performance. Significant group × time interactions were observed in the Trail Making Test Part A (TMT-A) and Continuous Performance Test (CPT), but not in Symbol Coding or Digit Span tests. Despite partial improvement in TMT-A and CPT tests, the cognitive-impaired subgroup's scores remained lower than those of the cognitive-preserved subgroup across all tests at the study endpoint. Multiple regression analysis indicated that longer illness duration, lower educational levels, and antipsychotic medication use may be risk factors for cognitive impairment. Conclusion: This study identifies distinguishable cognitive subgroups in acute depression, thereby confirming the presence of cognitive heterogeneity. The cognitive-impaired subgroup exhibits distinct symptoms and persistent cognitive deficits even after treatment. Screening for cognitive dysfunction may facilitate more targeted interventions. Clinical Trial Registration: https://www.chictr.org, identifier ChiCTR2400092796.
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 | 0.012 | 0.034 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| 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".