Diagnosis of Alzheimer's disease using neuropsychological testing improved by multivariate analyses

Abstract

Neuropsychological assessment aids in the diagnosis of Alzheimer’s disease (AD) by objectively establishing cognitive impairment from standardized tests. We present new criteria for diagnosis that use weighted combined scores from multiple tests. Our method employs two multivariate analyses: Principal Components Analysis (PCA) and discriminant analysis. PCA (N = 216 subjects) created more interpretable cognitive dimensions by resolving 49 test measures in our neuropsychological battery to 13 component scores for each subject. The component scores were used to build discriminant functions that classified each participant as either an early-stage AD (N = 55) or normal elderly (N = 78). Our discriminant function performed with high accuracy, sensitivity, and specificity (nearly all >90%) in the development, a cross-validation, and a new subjects validation. When contrasted to two different traditional empirical methods for diagnosis (using cutscores and defining AD as falling below 5% on two or more test domains), our results suggested that the multivariate method was superior in classification (approximately 20% more accurate).

Efficiency of Attentional Components in Elderly with Mild Neurocognitive Disorders Shown by the Attention Network Test

“…For instance, with a combination of verbal memory and executive function, the predictive accuracy of progression to Alzheimer's disease over 3 years is 86% [22]. A combination of memory and executive function measured by RT has been reported as the strongest predictor of progression to Alzheimer's disease [23]. Recently, the performance on specific executive function, such as inhibition, has been proved to be useful in distinguishing MCI subjects from healthy adults [24].…”

Cognitive Dimensions in Alzheimer`s Disease, Mild Cognitive Impairment, and Normal Elderly: Developing a Common Metric~!2009-11-20~!2010-02-01~!2010-03-12~!

“…On the practical level, it is advantageous for these groups to share the same underlying neuropsychological dimensions and thus justify the use of a common metric system (the factor solution) in measuring all the individuals. Thus knowing a novel individual’s diagnosis is not necessary when applying the factor structure to obtain factor scores, and these factor scores can be easily used in subsequent statistical analyses for many purposes, including analyzing group differences, diagnosing individuals with AD [48], and predicting MCI progression to AD in individuals. These latter issues concerning analyses at the individual level are particularly important for early identification of patients requiring therapeutic and pharmacologic interventions.…”

Latent structure of cognitive performance in the adult children study

“…Tasks tapping multiple domains were included as past research indicates that a wide range of measures and domains may be affected early in the course of the disease and in at-risk individuals (Bäckman, Jones, Berger, Laukka, & Small, 2005; Small, Rosnick, Fratiglioni, & Bäckman, 2004; Twamley, Ropacki, & Bondi, 2006). In addition, a multivariate approach may enhance the ability to detect cognitive changes (Chapman et al, 2010; Loewenstein et al, 2001; Ownby, Loewenstein, Schram, & Acevedo, 2004). As no single task provides an error-free estimate of performance in a given cognitive domain, the ACS battery involves multiple measures for each cognitive construct.…”

“…Some investigations have largely found measurement equivalence in comparisons between healthy older adults and symptomatic AD individuals (Chapman et al, 2010; Watts, Loskutova, Burns, & Johnson, 2013), between groups with and without a family history of AD (Dowling et al, 2010), and between groups with varying levels of cognitive impairment (Davis et al, 2003; Park et al, 2012). However, some studies have observed evidence of measurement non-invariance in comparisons between healthy older adults and individuals with questionable dementia or symptomatic AD (e.g., Delis, Jacobson, Bondi, Hamilton, & Salmon, 2003; Siedlecki et al, 2008).…”