Identifying the bridge between depression and mania: A machine-learning and network approach to bipolar disorder
Bibliographic record
Abstract
Objectives: Although the cyclic nature of bipolarity is almost by definition a network system, no research to date has attempted to specifically scrutinize the relation of the two bipolar poles, using network psychometrics. We used state-of-the-art network and machine-learning methods to identify symptoms, as well as relations thereof, that bridge depression and mania. Methods: Observational study that made use of mental health data (in particular, 12 symptoms for depression and 12 for mania; all binary) from a large, representative Canadian sample (i.e., Canadian Community Health Survey of 2002). Complete data (N=36,557; 54.6% female) were analysed using network psychometrics, in conjunction with a random forest algorithm, so as to examine the bidirectional interplay of depressive and manic symptoms. Results: Centrality analyses pointed to symptoms relating to emotionality and hyperactivity as being the most central aspects to depression and mania, respectively. The two syndromes were spatially segregated in the bipolar model and four symptoms appeared crucial in bridging them: sleep disturbance (insomnia and hypersomnia), anhedonia, suicidal ideation, and impulsivity. Our machine-learning algorithm validated the clinical utility of central and bridge symptoms (in the prediction of lifetime episodes of mania and depression), and further suggested that the centrality metrics map almost perfectly onto a data-driven measure of diagnostic utility. Conclusions: Our results replicate key findings from previous clinical network investigations on bipolar disorder; but also extend them by highlighting symptoms that bridge the two bipolar poles, as well as demonstrating their clinical utility. If replicated, these endophenotypes could prove fruitful targets for prevention/intervention strategies on bipolar disorder.
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 | 0.002 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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 | 0.000 | 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".