AUTHOR=Almubark Ibrahim , Chang Lin-Ching , Shattuck Kyle F. , Nguyen Thanh , Turner Raymond Scott , Jiang Xiong 

TITLE=A 5-min Cognitive Task With Deep Learning Accurately Detects Early Alzheimer's Disease

JOURNAL=Frontiers in Aging Neuroscience

VOLUME=Volume 12 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/aging-neuroscience/articles/10.3389/fnagi.2020.603179

DOI=10.3389/fnagi.2020.603179

ISSN=1663-4365

ABSTRACT=INTRODUCTION: The goal of this study was to investigate and compare the classification performance of machine learning with behavioral data from standard neuropsychological tests, a cognitive task, or both.
METHODS: A neuropsychological battery and a simple 5-minute cognitive task were administered to eight individuals with mild cognitive impairment (MCI), eight individuals with mild AD, and 41 demographically match controls. A fully connected multilayer perceptron (MLP) network and four supervised traditional machine learning algorithms were used.
RESULTS: MLP network outperformed traditional algorithms with the all datasets. In particularly, MLP network with a combination of summarized scores from neuropsychological tests and the cognitive task achieved ~90% sensitivity and ~90% specificity.
DISCUSSION: Deep learning with data from specific cognitive task(s) may have the potential to assist in the early diagnosis of Alzheimer’s disease.