Tackling Dynamic Prediction of Death in Patients with Recurrent Cardiovascular Events

• Activity Number: 197 - SPAAC Poster Competition
• Type: Topic Contributed
• Date/Time: Monday, August 8, 2022 : 2:00 PM to 3:50 PM
• Sponsor: Section on Risk Analysis
• Author(s): menglu liang* and Zheng Li and Liang Li and ming wang and Vernon M Chinchilli
• Companies: Penn State College of Medicine, Hershey, PA, USA and Novartis Pharmaceuticals and University of Texas MD Anderson Cancer Center, TX, USA and Penn State College of Medicine, Hershey, PA, USA and Pennsylvania State University College of Medicine
• Keywords: Recurrent events; Dynamic risk prediction; Mortality; Bayesian inference; Cardiovascular disease

Abstract

In cardiovascular disease field of study, recurrent events such as stroke or myocardial infarction (MI) are often encountered, leading to an increase in the risk of death. Evaluating the prognosis of patients and dynamically predicting the risk of death by taking the historical recurrent events into account is highly likely to enhance medical decisions with improved healthcare outcomes. Based upon most recently proposed joint modeling approaches within the Bayesian framework, we develop a dynamic prediction tool which can be applied for subject-level prediction of death with implementation in software packages. In particular, the prediction model is established by incorporating subject heterogeneity with subject-level random effects quantifying the part due to unobserved time-invarying factors and an extra copula function capturing the part caused by unmeasured time-dependent factors. Thereafter, given the pre-specified landmark time, the survival probability for a prediction horizon time of interest t can be estimated for each individual. The prediction accuracy is assessed by the Brier score and time-dependent ROC-AUC.