Automatic characterization of affective states in individuals with mood disorders based on the analysis of brain-heart interactions
Bibliographic record
Abstract
In 2019, approximately 9% of the Canadian population experienced mood disorders such as depression or bipolar disorder. The diagnosis and treatment of these conditions are often hindered by factors like social stigma, limited clinical resources, and the lack of reliable objective markers. To address this gap, this thesis explores the potential of integrating multiple bio-signals that capture both brain and heart activity to provide a more comprehensive understanding of mood disorders, particularly depression, during sleep. The primary aim of this research is to investigate the pathophysiological mechanisms underlying mood disorders by analyzing the interaction between sleep electroencephalogram (EEG) and electrocardiogram (ECG) signals. This study introduces a coherence metric as a potential interrelated biomarker for depression, linking brain and heart activity. A secondary analysis of polysomnography data from 46 individuals with depression and 40 healthy controls was conducted, revealing significant differences in brain-heart coherence of depression and healthy groups across sleep stages and EEG channels, particularly in the 0-8 Hz frequency bands. In parallel, this thesis develops SleepDepNet, a deep learning model designed to automate the detection of depression by leveraging EEG and ECG biomarkers such as relative power ratio, heart rate, and the introduced coherence metric. SleepDepNet combines convolutional neural networks with long short-term memory networks to analyze the temporal and spectral characteristics of these signals. The model demonstrated a high accuracy of 98.33% in classifying depression, validating the efficacy of using brain-heart interactions as diagnostic tools. These findings suggest that integrating EEG and ECG along with deep learning algorithms offers a promising approach for the objective identification of mood disorders and lays the groundwork for future research into their automated detection and prediction.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".