제목
[Seminar] Power and Commensurate Priors for Synthesizing Aggregate and Individual Patient-Level Data in Network Meta-Analysis
작성자
관리자
작성일
2017-11-13
조회수
415
첨부파일
파일 다운로드 171121 홍환희박사.pdf | 크기 : 60,740 byte | 다운 : 95

통계학과 세미나 공고

 

 

▣ 세미나 일정

√ 일 시 : 2017년 11월 21일 (화) 오전 11:00 ~ 11:40

√ 장 소 : 중앙대학교 경영경제대학 310관 410호

√ 발표자 : 홍환희 박사(Johns Hopkins Bloomberg School of Public Health)

√ 주 제 : Power and Commensurate Priors for Synthesizing Aggregate and Individual Patient-Level Data in Network Meta-Analysis

 

 

 

Abstract

Comparative effectiveness research helps answer what works best and provide evidence on the effectiveness, benefits, and harms of different treatments. When multiple sources of data exist on a particular question the evidence should be obtained by integrating those sources in a principled way. Network meta-analysis (NMA) is an extension of a traditional pairwise meta-analysis to compare multiple treatments simultaneously and take advantage of multiple sources of data. In NMA, it is often desirable to synthesize different types of studies, featuring aggregated data (AD) and individual patient-level data (IPD). However, existing methods do not sufficiently consider the quality of studies across different data types, and assume the treatment effects are exchangeable across all studies regardless of these types.


In this paper, we propose Bayesian hierarchical NMA models that allow us to borrow information adaptively across AD and IPD studies using power and commensurate priors. In addition, we incorporate covariate-by-treatment interactions to examine subgroup effects and discrepancy of the subgroup effects estimated in AD and IPD (i.e., ecological bias). The methods are validated and compared via extensive simulation studies, and then applied to an example in diabetes treatment comparing 28 oral anti-diabetic drugs. These methods enable us to integrate different types of data in network meta-analysis with flexible prior distributions and helps enhance comparative effectiveness research by providing a comprehensive understanding of treatment effects and effect modification from multiple sources of data.

 

 

Department of Statistics &

The Research Center for Data Science

목록