Imputation of systematically missing predictors in an individual participant data meta-analysis

Autor: Jolani, Shahab, Debray, Thomas P A, Koffijberg, Hendrik, van Buuren, Stef, Moons, Karel G M, Methodology and statistics for the behavioural and social sciences, Leerstoel Heijden
Přispěvatelé: University of Twente, Methodology and statistics for the behavioural and social sciences, Leerstoel Heijden
Jazyk: angličtina
Rok vydání: 2015
Předmět:
Multivariate analysis
multiple imputation
MULTIPLE-IMPUTATION
Mathematical computing
Statistical distribution
Computer science
Epidemiology
Logistic regression
Multivariate imputation by chained equation
LS - Life Style
missing data
REML ESTIMATION
Life
Risk Factors
Deep vein thrombosis
Statistics
Econometrics
Maximum likelihood method
Prevalence
Multilevel multiple imputation
Imputation (statistics)
IPD meta-analysis
Venous Thrombosis
Medicine(all)
RISK
Covariance
Stratified multiple imputation
Multilevel model
Calculation
LOGISTIC-REGRESSION
multilevel model
Algorithm
Meta-analysis
FULLY CONDITIONAL SPECIFICATION
Statistical model
Healthy Living
Algorithms
Simulation
Human
Statistics and Probability
LOGISTIC-REGRESSION ANALYSIS
Missing data
MODELS
MULTIVARIATE IMPUTATION
Risk Assessment
Generalized linear mixed model
VALIDATION
Resche Rigon method
Meta-Analysis as Topic
Predictive Value of Tests
Linear system
Humans
prediction research
Computer Simulation
PATIENT DATA
Probability
FRAMEWORK
Prediction research
THROMBOSIS
Traditional multiple imputation
Linear Models
Nonlinear system
Multiple imputation
ELSS - Earth
Life and Social Sciences
Healthy for Life
Prediction
Acoustics and Audiology
Controlled study
Zdroj: Statistics in Medicine, 34(11), 1841. John Wiley and Sons Ltd
Statistics in medicine, 34(11), 1841-1863. Wiley
Statistics in Medicine, 34(11), 1841-1863. John Wiley & Sons Inc.
Statistics in Medicine, 11, 34, 1841-1863
ISSN: 0277-6715
DOI: 10.1002/sim.6451
Popis: Individual participant data meta-analyses (IPD-MA) are increasingly used for developing and validating multivariable (diagnostic or prognostic) risk prediction models. Unfortunately, some predictors or even outcomes may not have been measured in each study and are thus systematically missing in some individual studies of the IPD-MA. As a consequence, it is no longer possible to evaluate between-study heterogeneity and to estimate study-specific predictor effects, or to include all individual studies, which severely hampers the development and validation of prediction models.Here, we describe a novel approach for imputing systematically missing data and adopt a generalized linear mixed model to allow for between-study heterogeneity. This approach can be viewed as an extension of Resche-Rigon's method (Stat Med 2013), relaxing their assumptions regarding variance components and allowing imputation of linear and nonlinear predictors.We illustrate our approach using a case study with IPD-MA of 13 studies to develop and validate a diagnostic prediction model for the presence of deep venous thrombosis. We compare the results after applying four methods for dealing with systematically missing predictors in one or more individual studies: complete case analysis where studies with systematically missing predictors are removed, traditional multiple imputation ignoring heterogeneity across studies, stratified multiple imputation accounting for heterogeneity in predictor prevalence, and multilevel multiple imputation (MLMI) fully accounting for between-study heterogeneity.We conclude that MLMI may substantially improve the estimation of between-study heterogeneity parameters and allow for imputation of systematically missing predictors in IPD-MA aimed at the development and validation of prediction models. Copyright (c) 2015John Wiley & Sons, Ltd.
Databáze: OpenAIRE
Externí odkaz: