Use of Sleep-Related Variables to Predict Time to Death in Patients with Heart Failure in the ADVENT-HF Trial
Bibliographic record
Abstract
Background: In heart failure with reduced ejection fraction (HFrEF), we showed that longer Cheyne-Stokes respiration (CSR) cycle length (CL) and lung-to-finger-circulation-time (LFCT) are associated with higher mortality. Herein, we aimed to develop a model to predict time to death using sleep variables. Methods: We extracted 20 CSR cycles from the baseline polysomnogram (PSG) of 60 ADVENT-HF patients with CSR who died during follow-up (Lyons et al., 2017). We calculated and averaged the CSR CL from the beginning of 1 apnea to the beginning of the next as well as apnea length, hyperpnea length, LFCT, respiratory rate, SaO2, time to peak tidal volume during hyperpnea, and AHI. We also assessed clinical variables including sex, age, BMI, ejection fraction (EF), atrial fibrillation, myocardial infarction, mitral regurgitation, NYHA class, and peak-flow-adaptive-servo-ventilation treatment. To predict time to death, we employed a fusion modeling approach with a feature selection technique that combined classification and regression. We divided patients into 3 mortality classes based on survival duration: <1 year, 1-3 years, and 3-5 years. We applied regression within each class to estimate time to death. Results: Mean survival was 706.9 ± (SD) 477.4 days. Our model used features including EF, CL, LFCT, age, BMI, and AHI to estimate time to death with an average error of 143±26 days, or 20%. Conclusion: This study demonstrates the potential role of CSR-related features such as CL and LFCT to predict time to death in patients with HFrEF. It reinforces the importance of analyzing CSR patterns from PSG in HFrEF and that these variables may contribute to comprehensive risk assessment.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.000 | 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 | 0.001 |
| 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".