SCALAR ON NETWORK REGRESSION VIA BOOSTING

• 成果类型: Article
• 署名作者: Morris, Emily L.; He, Kevin; Kang, Jian
• 署名单位: University of Michigan System; University of Michigan
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/22-AOAS1612
• 发表日期: 2022
• 页码: 2755-2773
• 关键词: on-image regression; neuroimaging data; connectivity; PERSPECTIVE; selection; models; cortex

摘要

Neuroimaging studies have a growing interest in learning the association between the individual brain connectivity networks and their clinical char-acteristics. It is also of great interest to identify the sub-brain networks as biomarkers to predict the clinical symptoms, such as disease status, poten-tially providing insight on neuropathology. This motivates the need for devel-oping a new type of regression model where the response variable is scalar, and predictors are networks that are typically represented as adjacent matrices or weighted adjacent matrices to which we refer as scalar-on-network regres-sion. In this work we develop a new boosting method for model fitting with subnetwork markers selection. Our approach, as opposed to group lasso or other existing regularization methods, is, essentially, a gradient descent algo-rithm leveraging known network structure. We demonstrate the utility of our methods via simulation studies and analysis of the resting-state fMRI data in a cognitive developmental cohort study.