Leach Justin M, Edwards Lloyd J, Kana Rajesh, Visscher Kristina, Yi Nengjun, Aban Inmaculada
Department of Biostatistics, University of Alabama at Birmingham, Birmingham, Alabama, United States of America.
Department of Psychology, University of Alabama, Tuscaloosa, Alabama, United States of America.
PLoS One. 2022 Feb 3;17(2):e0262367. doi: 10.1371/journal.pone.0262367. eCollection 2022.
Alzheimer's disease (AD) is the leading cause of dementia and has received considerable research attention, including using neuroimaging biomarkers to classify patients and/or predict disease progression. Generalized linear models, e.g., logistic regression, can be used as classifiers, but since the spatial measurements are correlated and often outnumber subjects, penalized and/or Bayesian models will be identifiable, while classical models often will not. Many useful models, e.g., the elastic net and spike-and-slab lasso, perform automatic variable selection, which removes extraneous predictors and reduces model variance, but neither model exploits spatial information in selecting variables. Spatial information can be incorporated into variable selection by placing intrinsic autoregressive priors on the logit probabilities of inclusion within a spike-and-slab elastic net framework. We demonstrate the ability of this framework to improve classification performance by using cortical thickness and tau-PET images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to classify subjects as cognitively normal or having dementia, and by using a simulation study to examine model performance using finer resolution images.
阿尔茨海默病（AD）是痴呆症的主要病因，已受到大量研究关注，包括使用神经影像生物标志物对患者进行分类和/或预测疾病进展。广义线性模型，如逻辑回归，可用作分类器，但由于空间测量值相互关联且数量往往多于受试者，惩罚模型和/或贝叶斯模型是可识别的，而经典模型通常不可识别。许多有用的模型，如弹性网络和尖峰和平板套索，执行自动变量选择，可去除无关预测变量并降低模型方差，但这两种模型在选择变量时都未利用空间信息。通过在尖峰和平板弹性网络框架内对纳入的逻辑概率施加内在自回归先验，可以将空间信息纳入变量选择。我们通过使用来自阿尔茨海默病神经影像倡议（ADNI）的皮质厚度和tau-PET图像将受试者分类为认知正常或患有痴呆症，以及通过使用模拟研究来检验使用更高分辨率图像时的模型性能，证明了该框架改善分类性能的能力。
