Stratifying cardiovascular benefits from GLP-1RA: a multisource analysis of patient-level CVOT and real-world data using AI-driven methods
Authors' conclusion
This study supports the integration of individual data from CVOT with those from EHR to confirm the transposition of results from CVOT to real-world populations, and enables the identification and validation of subgroups with greater cardiovascular benefits from cardioprotective treatment such as GLP-1RA treatment. This precision medicine approach represents a new framework for deploying cardiovascular prevention strategies in T2D.
Study context
- Population
- Individuals with T2D; data from 2 cardiovascular outcome trials (CVOTs) (LEADER, SUSTAIN-6) and a real-world study (DARWIN-T2D), with external new-user cohorts2 CVOTs + real-world study
- Comparison
- GLP-1 RA vs comparators
- Outcome
- 3P-MACE reduction by GLP-1RA
Methodological detailsmultisource, individual-level data, training/test setting, external validation
- Multisource
- Individual-level data
- Training/test setting
- External validation
Pooled result
As reported in the abstract
Aged >71 years without myocardial infarction (MI)/stroke: greatest relative benefit, HR (95% CI), test set
0.46
0.24–0.89
Aged >71 years without MI/stroke: greater absolute risk reduction than other subgroups, ARR
4.5% (1.2-7.7) (95% CI)
Difference between subgroups
Gail-Simon p = 0.02
Further pooled results
3P-MACE in subgroup aged >71 years without MI/stroke, external validation cohort
- HR
- 0.67 (0.51-0.89) (95% CI)
- ARR
- 3.8% (1.5-6.1) (95% CI)
- Significant differences in absolute risk reduction
- P < 0.05
- External validation cohort
Original publication
Composed by AI from the published abstract and checked against it. How Briefs are made →