Causal Machine Learning for Comparative Effectiveness of GLP-1 RA versus SGLT2i in Heart Failure Using Real-World EHR Data
Han, G. Y.; Kalogeropoulos, A. P.; Butzin-Dozier, Z.; Wong, R.; Wang, F.
Show abstract
Clinicians lack precision medicine tools to estimate individualized treatment effects for patients with heart failure (HF). Causal machine learning leveraging electronic health records can estimate both average and individualized treatment effects, enabling estimation of treatment heterogeneity. Using Stony Brook University Hospital data, we compared the effectiveness of glucagon-like peptide-1 receptor agonists (GLP-1 RA) versus sodium-glucose cotransporter 2 inhibitors (SGLT2i) in patients with HF. Under a doubly robust framework, we found a stable population-average effect: GLP-1 RA was associated with a lower risk than SGLT2i for a 1-year composite outcome of all-cause mortality or HF-related hospitalization. Heterogeneity analyses provided limited evidence for individualized treatment selection, although subgroup tests identified loop diuretic use, body mass index, and estimated glomerular filtration rate as potential effect modifiers. While these models hold promise for translating observational data into actionable precision care, careful assessment of causal assumptions and rigorous validation are essential before clinical implementation.
Matching journals
The top 10 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Biomarker panels for improved risk prediction and enhanced biological insights in patients with atrial fibrillation 94%
- Genome-wide association analysis and Mendelian randomization proteomics identify novel protein biomarkers and drug targets for primary prevention of heart failure 92%
- Genetic Architecture of Heart Failure with Preserved versus Reduced Ejection Fraction 92%
Similar papers in this journal
- Development and Multinational Validation of an Ensemble Deep Learning Algorithm for Detecting and Predicting Structural Heart Disease Using Noisy Single-lead Electrocardiograms 94%
- Simple Models Versus Deep Learning in Detecting Low Ejection Fraction From The Electrocardiogram 92%
- Development and Validation of a parsimonious AI-Based Risk Score for Mortality in Heart Failure: A UK cohort study 92%
Similar papers in this journal
- Aptamer Proteomics for Biomarker Discovery in Heart Failure with Reduced Ejection Fraction 93%
- Genetically Predicted IL-18 Inhibition and Risk of Cardiovascular Events: A Mendelian Randomization Study 92%
- Effects of catheter-based renal denervation in hypertension: a systematic review and meta-analysis 92%
Similar papers in this journal
Similar papers in this journal
- Comparative Effectiveness of Second-line Antihyperglycemic Agents for Cardiovascular Outcomes: A Large-scale, Multinational, Federated Analysis of the LEGEND-T2DM Study 96%
- Lipid-Modulating Agents for Prevention or Treatment of COVID-19 in Randomized Trials 90%
- Assessment of valvular function in over 47,000 people using deep learning-based flow measurements 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.