Neuropsychological test selection for cognitive impairment classification: A machine learning approach

Introduction: Reducing the amount of testing required to accurately detect cognitive impairment is clinically relevant. The aim of this research was to determine the fewest number of clinical measures required to accurately classify participants as healthy older adult, mild cognitive impairment (MCI), or dementia using a suite of classification techniques. Method: Two variable selection machine learning models (i.e., naive Bayes, decision tree), a logistic regression, and two participant datasets (i.e., clinical diagnosis; Clinical Dementia Rating, CDR) were explored. Participants classified using clinical diagnosis criteria included 52 individuals with dementia, 97 with MCI, and 161 cognitively healthy older adults. Participants classified using CDR included 154 individuals with CDR = 0, 93 individuals with CDR = 0.5, and 25 individuals with CDR = 1.0+. A total of 27 demographic, psychological, and neuropsychological variables were available for variable selection. Results: No significant difference was observed between naive Bayes, decision tree, and logistic regression models for classification of both clinical diagnosis and CDR datasets. Participant classification (70.0-99.1%), geometric mean (60.9-98.1%), sensitivity (44.2-100%), and specificity (52.7-100%) were generally satisfactory. Unsurprisingly, the MCI/CDR = 0.5 participant group was the most challenging to classify. Through variable selection only 2-9 variables were required for classification and varied between datasets in a clinically meaningful way. Conclusions: The current study results reveal that machine learning techniques can accurately classify cognitive impairment and reduce the number of measures required for diagnosis.