Personalized Lifetime Prediction of Survival and Treatment Benefit in Patients with Heart Failure with Reduced Ejection Fraction: The LIFE-HF Model
Bibliographic record
Abstract
AIMS: Although trials have proven the group-level effectiveness of various therapies for heart failure with reduced ejection fraction (HFrEF), important differences in absolute effectiveness exist between individuals. We developed and validated the LIFEtime-perspective for Heart Failure (LIFE-HF) model for the prediction of individual (lifetime) risk and treatment benefit in patients with HFrEF. METHODS AND RESULTS: Cox proportional hazards functions with age as the time scale were developed in the PARADIGM-HF and ATMOSPHERE trials (n = 15 415). Outcomes were cardiovascular death, heart failure (HF) hospitalization or cardiovascular death, and non-cardiovascular mortality. Predictors were age, sex, New York Heart Association class, prior HF hospitalization, diabetes mellitus, extracardiac vascular disease, systolic blood pressure, left ventricular ejection fraction, N-terminal pro-B-type natriuretic peptide, and glomerular filtration rate. The functions were combined in life-tables to predict individual overall and HF hospitalization-free survival. External validation was performed in the SwedeHF registry, ASIAN-HF registry, and DAPA-HF trial (n = 51 286). Calibration of 2- to 10-year risk was adequate, and c-statistics were 0.65-0.74. An interactive tool was developed combining the model with hazard ratios from trials to allow estimation of an individual's (lifetime) risk and treatment benefit in clinical practice. Applying the tool to the development cohort, combined treatment with a mineralocorticoid receptor antagonist, sodium-glucose cotransporter 2 inhibitor, and angiotensin receptor-neprilysin inhibitor was estimated to afford a median of 2.5 (interquartile range [IQR] 1.7-3.7) and 3.7 (IQR 2.4-5.5) additional years of overall and HF hospitalization-free survival, respectively. CONCLUSION: The LIFE-HF model enables estimation of lifelong overall and HF hospitalization-free survival, and (lifetime) treatment benefit for individual patients with HFrEF. It could serve as a tool to improve the management of HFrEF by facilitating personalized medicine and shared decision-making.
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 | 0.006 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".