Clinical Variables Contributing to Identification of Mild Cognitive Impairment Individuals With Defined ATN Profile

Abstract

AbstractBackgroundThe framework globally used to classify Alzheimer’s Disease stages for research purposes includes three core biomarkers: A) Aβ burden; T) tau pathology; and N) neuronal injury. A lack of consensus exists in linking cognitive and behavioral tests used in everyday clinical practice to biological stages of dementia as defined by the ATN classification. The aim of the current study is to identify the clinical variables that best classify individuals into biologically defined cognitive profiles.MethodA total of 751 subjects, from the Alzheimer’s Disease Neuroimaging Initiative cohort, were categorized into seven ATN groups: 112 cognitively unimpaired with ATN‐; 46 cognitively unimpaired with ATN or AT+; 65 cognitively unimpaired with T, N or TN+; 128 amnestic Mild Cognitive Impairment (aMCI) with ATN‐; 223 aMCI with ATN or AT+; 94 aMCI with T, N or TN+ and 83 dementia with ATN or AT+. The groups for which the features exhibited differences during data exploration were classified employing 28 cognitive, behavioral, and demographic features using a supervised machine learning algorithm, specifically, a random forest classifier in combination with a synthetic oversampling technique.ResultWe found that the selected features were not able to distinguish between all seven groups and in particular between the three cognitively unimpaired groups. Therefore, classification was only performed for the three ATN‐defined aMCI groups achieving 58% overall accuracy. The Logical Delayed Recall was the most relevant feature (explaining 17% of the variance), followed by the Alzheimer’s Disease Assessment Scale‐Cognitive Subscale 13 (16%), Everyday Cognition Informant (8%), and Alzheimer’s Disease Assessment Scale 4 (8%). Marital status, Everyday Cognition Patient and sex were not relevant (0%).ConclusionCognitive and behavioral tests were not able to accurately distinguish cognitively unimpaired individuals with different biological profiles. Although accuracy could be improved, our first results showed that a test of delayed memory, one of general cognition, and one on activities of daily living are relevant variables for distinguishing between patients with aMCI and different biological profiles. During diagnosis, treatment monitoring, or in research contexts, these variables might be informative in differentiating the three ATN‐defined aMCI profiles, especially when biomarkers are not available.