다음과 같이 초청특강을 실시하오니 많은참여바랍니다.

1. 일시 : 2023년 12월 21일 (목), 오후 4시 30분 -

2. 장소 : 자연대연구실험동 222호

3. 연사 : 송성호 교수 (Division of Statistics and Data Science, Univ. of Cincinnati)

4. 연제 : Multivariate Joint Models with Integrated Fractional Brownian motion for Dynamic Prediction of Longitudinal and survival Data

Abstract

  Numerous longitudinal outcomes are collected in order to conduct a thorough investigation of the multidimensional impairment caused by a disease. When a patient’s lung function rapidly deteriorates, it alerts health care professionals to monitor the patient’s illness development and make informed and timely medical decisions, such as preparing the patient for lung transplantation. Since cystic fibrosis is a multisystem condition, we propose a multivariate joint model that employs a flexible covariance structure such as Integrated Fractional Brownian motion to effectively capture the highly variable nature of these longitudinal processes while modeling lung function, and growth simultaneously. This model may improve the prediction accuracy of survival probability when compared to a univariate joint model that employs random-slopes random-intercepts model to depict the longitudinal process. Cox proportional hazards model was used as our time-to-event submodel, which included, slopes of true longitudinal trajectories in addition to value of true longitudinal trajectories and a set of baseline covariates. We employed Bayesian methodologies to develop our model, as well as obtain parameter estimates and inferences. Along with developing a dynamic prediction framework for predicting the future outcome trajectories and predictive probabilities of CF patients using clinically relevant target functions, we also developed a method for calculating dynamic event-free probabilities using multivariate loniigitudinal data. Our suggested model is assessed using simulations and is applied to the US Cystic Fibrosis Foundation?Patient Registry (CFF-PR) data set.