1088 HEART RATE SLEEP PROFILE: A NEW BIOMARKER FOR DEPRESSION?
Bibliographic record
Abstract
Sleep disturbances may play an important role in the pathophysiology of both depression and cardiovascular dysfunctions. Previous observations suggested atypical patterns of heart rate changes in people with depression, often marked by elevated and unstable heart rate during sleep. This study assessed the validity of novel biomarkers based on heart rate changes across the sleep period to discriminate between individuals with depression and healthy controls. Retrospective data was collated in 993 adults: 545 with unipolar depressive syndromes referred to a specialized sleep clinic (74% females, mean±SD: 45 ± 16 years old), and 448 healthy controls (55% females, mean±SD: 40 ± 18 years old). Electrocardiography started before bedtime and extended beyond sleep offset. Sleep-based heart rate profiles were defined by a classification algorithm using a panel of temporal and frequency domain variables designed to distinguish between depression and control cases. A subset of 630 cases (315 depression & 315 controls) was randomly selected for training the machine-learning algorithm, and the remaining 259 cases (125 depression & 134 controls) were used for testing the algorithm. This process was repeated ten times with different subsets to assess classification stability. After training, the algorithm classified individuals with depressive syndrome and healthy controls with a mean accuracy of 86%. More specifically, 82% of the depression cases were correctly identified by the algorithm (i.e. sensitivity) and, of the cases not classified as depression by the algorithm, 88% were from the control group (i.e. specificity). The algorithm’s ability to distinguish between clinical groups based on heart rate changes across sleep is encouraging for the identification of objective biomarkers of depression. The pathophysiological mechanisms underlying cardiovascular changes across sleep in the context of depression remain to be further investigated. Yet, the present results suggest that heart rate profiles during sleep may be useful as adjunctive assessment measures for depression. This study was partly supported by a fellowship from the Canadian Institutes of Health Research.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".