Joint longitudinal and time‐to‐event modelling compared with standard Cox modelling in patients with type 2 diabetes with and without established cardiovascular disease: An analysis of the Exenatide Study of Cardiovascular Event Lowering (EXSCEL) trial
Authors' conclusion
The analysis demonstrates that the joint modelling approach, considering trajectories of cardiovascular risk factors, provides superior predictive performance compared to standard RPTs that use only a single timepoint.
Study context
- Population
- Patients with T2D with and without established cardiovascular disease (CVD) in the EXSCEL trial
- Comparison
- Bayesian joint model vs Cox proportional hazards model
- Primary endpoint
- Predictive performance for major adverse cardiovascular events (MACE): time-dependent AUC of ROC (aROC) for discrimination and time-dependent Brier score for calibration
Methodological detailsprediction modelling, Bayesian joint model vs Cox proportional hazards model
- Prediction modelling
- Bayesian joint model vs Cox proportional hazards model
Primary result
As reported in the abstract
aROC for MACE prediction, participants without history of CVD
aROC of systolic blood pressure (SBP), single vs repeated measurements
0.62 to 0.69
aROC of SBP and low-density lipoprotein cholesterol (LDL-C), single vs repeated measurements
0.67 to 0.80
Further findings
- Improvement evident with and without history of CVD, more pronounced in those without
Original publication
Joint longitudinal and time‐to‐event modelling compared with standard Cox modelling in patients with type 2 diabetes with and without established cardiovascular disease: An analysis of the EXSCEL trial. Diabetes Obes Metab. Published 1 February 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →