Machine Learning Reveals How Depression Influences Chest Pain Localisation and Its Predictive Value for Coronary Artery Disease
Bibliographic record
Abstract
BACKGROUND: Depression is independently associated with chest pain and increased cardiovascular risk, regardless of coronary artery disease (CAD) status. However, limited research has examined how chest pain characteristics differ in individuals with and without depression. This study evaluated the relationship between depression and chest pain localisation to inform CAD risk assessment. METHODS: Data from the National Health and Nutrition Examination Survey from 2005 to 2020 were analysed for adults completing the chest pain questionnaire. Survey-weighted propensity score matching created depression-stratified cohorts. Chest pain localisation and inter-regional correlations were compared using survey design-adjusted methods. Random forest models with survey-weighted bootstrap replicates were used to estimate the relative importance of pain locations in predicting CAD, stratified by depression status. RESULTS: A total of 2208 individuals were matched (1104 per cohort). Depressed individuals more frequently reported chest pain in the lower sternum (P = 0.045), left chest (P = 0.002), and epigastrium (P = 0.039). In depressed individuals, atypical pain regions (epigastrium, lower sternum, neck, arms) were more predictive of CAD, whereas in nondepressed individuals, typical regions (chest, upper sternum) were stronger predictors. These findings were robust to temporal validation and stricter definitions of depression. CONCLUSIONS: Depression modifies the predictive value of chest pain localisation for CAD. A "depressed chest pain profile" involving nontraditional locations was more strongly associated with CAD in those with depression, and a more central "nondepressed pain profile" was more predictive in those without. These findings underscore the importance of integrating mental health context into chest pain evaluation.
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 | 0.004 | 0.022 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".