Optimizing Neuropsychological Assessments for Cognitive, Behavioral, and Functional Impairment Classification: A Machine Learning Study

Abstract

Subjects with Alzheimer's disease (AD) show loss of cognitive functions and change in behavioral and functional state affecting the quality of their daily life and that of their families and caregivers. A neuropsychological assessment plays a crucial role in detecting such changes from normal conditions. However, despite the existence of clinical measures that are used to classify and diagnose AD, a large amount of subjectivity continues to exist. Our aim was to assess the potential of machine learning in quantifying this process and optimizing or even reducing the amount of neuropsychological tests used to classify AD patients, also at an early stage of impairment. We investigated the role of twelve state-of-the-art neuropsychological tests in the automatic classification of subjects with none, mild, or severe impairment as measured by the clinical dementia rating (CDR). Data were obtained from the ADNI database. In the groups of measures used as features, we included measures of both cognitive domains and subdomains. Our findings show that some tests are more frequently best predictors for the automatic classification, namely, LM, ADAS-Cog, AVLT, and FAQ, with a major role of the ADAS-Cog measures of delayed and immediate memory and the FAQ measure of financial competency.

Figure 1

Representative example for one round and one iteration (CDR = 1 versus CDR = 0, round #1, iteration #1) of features ordered according to their FDR.

Figure 2

Features ordered according to their individual classification accuracy for CDR = 1 versus CDR = 0 (a), CDR = 0.5 versus CDR = 0 (b), and CDR = 1 versus CDR = 0.5 (c), using the feature reduction guided by the neuropsychologists. Results were obtained as average across all rounds (10) and iterations (100) but for each feature independently. Features are ranked in descending significance with respect to accuracy.

Figure 3

Highest accuracy of classification as a function of the configuration (combination of input features) in the inner loop of the nested CV. Performances are reported for CDR = 1 versus CDR = 0 (blue), CDR = 0.5 versus CDR = 0 (red), and CDR = 1 versus CDR = 0.5 (green), using the features chosen by the neuropsychologists. Results were obtained as average across all rounds (10) and iterations (100).