Coronary disease & ACSDiagnostic or prognostic study
Advancing in-hospital mortality prediction for acute myocardial infarction: An analysis from the American Heart Association Get With The Guidelines–Coronary Artery Disease Registry
- development and validation of a contemporary in-hospital mortality risk model
- independent validation cohort
- subgroup and sensitivity analyses
Authors' conclusion
The GWTG-CAD model suite advances AMI mortality prediction through 2 complementary approaches: the LightGBM model offers superior discrimination for identifying high-risk patients across diverse subgroups, while the generalized linear mixed model provides a transparent tool for institutional benchmarking and quality improvement. Broader external validation is needed before clinical deployment.
Study context
- Population
- Patients with Acute Myocardial Infarction (AMI) in the American Heart Association (AHA) Get with The Guidelines-Coronary Artery Disease (GWTG-CAD) Registrydevelopment cohort from 605 hospitals, validation cohort admitted in 2023 · Development cohort (admitted October 1, 2019, to December 31, 2022) 201,191 · Independent validation cohort (admitted in 2023) 70,302
- Comparison
- GWTG-CAD in-hospital mortality model benchmarked against the legacy ACTION Registry-GWTG model
Performance
As reported in the abstract
Light Gradient Boosting Machine (LightGBM)-based GWTG-CAD model
0.874
AUROC · 95% confidence intervals 0.867–0.880
ACTION Registry-GWTG model
0.859
AUROC · 95% confidence intervals 0.852–0.867
generalized linear mixed model
0.865
AUROC
Further findings
Predictor contribution
- Comorbidities, transportation method, and community-level socioeconomic factors contributed meaningful predictive value beyond traditional predictors
Original publication
Summarised from the published abstract; every number is checked against it