Abstract 15516: Predicting Heart Failure Hospitalization in Type 2 Diabetes Mellitus: Validation of the TRS-HFDM Score in the ACCORD Trial
Bibliographic record
Abstract
Background: Patients with type 2 diabetes mellitus (T2DM) are at an increased risk for developing heart failure (HF), and clinical models are needed to identify patients with a greater risk for HF hospitalization (HHF). The Thrombolysis in Myocardial Infarction Risk Score for Heart Failure in Diabetes (TRS-HFDM) was recently developed and validated to predict HHF in patients with T2DM in two large clinical trials (SAVOR-TIMI 53 and DECLARE-TIMI 58). We aimed to validate the TRS-HFDM in another cohort of patients with T2DM. Methods: We validated the TRS-HFDM score in 5,123 patients with T2DM for fatal or non-fatal HHF in the placebo arm of the ACCORD (Action to Control Cardiovascular Risk in Diabetes Study Group). The TRS-HFDM included: prior HF, history of atrial fibrillation, coronary artery disease, estimated glomerular filtration rate, and urine albumin-to-creatinine ratio. We evaluated discrimination with the Harrell C index, and calibration by comparing observed event rates for HHF with predicted risk, and the Nam-D’Agostino statistic. Results: During a mean follow up of 4.8 years, 212 patients (4.14%) experienced at least one HHF. The mean age was 63 ±6.7 years, and 38% were female. The baseline hemoglobin A1C was 8.3%, and 36% were on insulin. The ACCORD patients had less comorbidities with a lower proportion of patients with renal dysfunction (8% vs. 16% vs. 17%), established cardiovascular disease (35% vs.79% vs. 41%) and pre-existing HF (5% vs. 13% vs. 10%) compared to patients enrolled in the SAVOR-TIMI 53 and DECLARE TIMI-58 trials respectively. In our cohort, the TRS-HFDM score predicted well HHF events with a Harrel C index of 0.78. The integer-based score was well calibrated, with the observed Kaplan-Meier HHF rates closely predicting the Kaplan-Meier event rates at the end follow up (Nam D`Agostino test: 65.39 (p<0.0001). Discussion: Our findings confirm the applicability of the TRS-HFDM in a large cohort of patients with T2DM with less high-risk features than the SAVOR-TIMI 53 and DECLARE-TIMI 58 populations. Future validation of this risk score in observational cohort studies is needed to evaluate its external validity in a general clinical setting.
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 | 0.007 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 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) | 0.002 | 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".