Title: Mass univariate relative risk regression for longitudinal binary-valued neuroimaging data
Authors: Petya Kindalova - GlaxoSmithKline (United Kingdom)
Michele Veldsman - University of Cambridge (United Kingdom)
Thomas Nichols - University of Oxford (United Kingdom) [presenting]
Ioannis Kosmidis - University of Warwick and The Alan Turing Institute (United Kingdom)
Abstract: There is growing interest in binary-valued brain images from MRI. Binary image data can identify the tissue damaged by a stroke, multiple sclerosis lesions in white matter, or bright spots called white matter hyperintensities. We recently proposed a mass univariate approach to modelling crossectional data that addresses the problem of low base rate with a penalised maximum likelihood approach with a probit or logistic model. We consider the additional challenge of longitudinal data. Users often want to interpret results as relative risks instead of odds-ratios, but a log-link with binomial variance function may lead to estimation instabilities when event probabilities are close to 1. To address these issues, we use generalized estimating equations with log-link regression structures with identity variance function and unknown dispersion parameter, with a penalty on the GEE of the gradient of the Jeffreys prior to avoid infinite parameter estimates. Our findings from extensive simulation studies show significant improvement over the standard log-link generalized estimating equations by providing finite estimates and achieving convergence when boundary estimates occur. The real data application on UK Biobank brain lesion maps further reveals the instabilities of the standard log-link generalized estimating equations for a large-scale data set and demonstrates the clear interpretation of relative risk in clinical applications.