Neuroscience and Mental Health Institute, University of Alberta.
Department of Psychology, University of Alberta.
Neuropsychology. 2021 Nov;35(8):889-903. doi: 10.1037/neu0000775. Epub 2021 Sep 27.
Executive function (EF) performance and structure in nondemented aging are frequently examined with variable-centered approaches. Person-centered analytics can contribute unique information about classes of persons by simultaneously considering EF performance and structure. The risk predictors of these classes can then be determined by machine learning technology. Using data from the Victoria Longitudinal Study we examined two goals: (a) detect different underlying subgroups (or classes) of EF performance and structure and (b) test multiple risk predictors for best discrimination of these detected subgroups. We used a classification sample (n = 778; = 71.42) for the first goal and a prediction subsample ( = 570; = 70.10) for the second goal. Eight neuropsychological measures represented three EF dimensions (inhibition, updating, shifting). Fifteen predictors represented five domains (genetic, functional, lifestyle, mobility, demographic). First, we observed two distinct classes: (a) lower EF performance and unidimensional structure (Class 1) and (b) higher EF performance and multidimensional structure (Class 2). Second, Class 2 was predicted by younger age, more novel cognitive activity, more education, lower body mass index, lower pulse pressure, female sex, faster balance, and more physical activity. Data-driven modeling approaches tested the possibility of an EF aging class that displayed both preserved EF performance levels and sustained multidimensional structure. The two observed classes differed in both performance level (lower, higher) and structure (unidimensional, multidimensional). Machine learning prediction analyses showed that the higher performing and multidimensional class was associated with multiple brain health-related protective factors. (PsycInfo Database Record (c) 2021 APA, all rights reserved).
执行功能（EF）在未患痴呆的衰老中的表现和结构通常采用变量为中心的方法进行检查。以个体为中心的分析可以通过同时考虑 EF 表现和结构，为个体的类别提供独特的信息。然后可以通过机器学习技术确定这些类别的风险预测因素。使用来自维多利亚纵向研究的数据，我们检查了两个目标：（a）检测 EF 表现和结构的不同潜在亚组（或类别）；（b）测试多种风险预测因素，以最佳区分这些检测到的亚组。我们使用分类样本（n = 778； = 71.42）来实现第一个目标，使用预测子样本（n = 570； = 70.10）来实现第二个目标。八项神经心理学测试代表了三个 EF 维度（抑制、更新、转换）。十五个预测因素代表了五个领域（遗传、功能、生活方式、移动性、人口统计学）。首先，我们观察到两个不同的类别：（a）EF 表现较低且结构单一（类别 1）；（b）EF 表现较高且结构多维（类别 2）。其次，类别 2 由年龄较小、更多新颖的认知活动、更高的教育程度、较低的体重指数、较低的脉压、女性、更快的平衡和更多的身体活动预测。数据驱动的建模方法检验了 EF 衰老类别是否具有保存的 EF 表现水平和维持的多维结构的可能性。观察到的两个类别在表现水平（较低、较高）和结构（单一、多维）上均有所不同。机器学习预测分析表明，表现较高且多维的类别与多个与大脑健康相关的保护因素相关。（PsycInfo 数据库记录（c）2021 APA，保留所有权利）。
