An Automatic Assessment System for Alzheimer's Disease Based on Speech Using Feature Sequence Generator and Recurrent Neural Network
Journal
Scientific Reports
Journal Volume
9
Journal Issue
1
Pages
-
Date Issued
2019
Author(s)
Abstract
Alzheimer disease and other dementias have become the 7th cause of death worldwide. Still lacking a cure, an early detection of the disease in order to provide the best intervention is crucial. To develop an assessment system for the general public, speech analysis is the optimal solution since it reflects the speaker’s cognitive skills abundantly and data collection is relatively inexpensive compared with brain imaging, blood testing, etc. While most of the existing literature extracted statistics-based features and relied on a feature selection process, we have proposed a novel Feature Sequence representation and utilized a data-driven approach, namely, the recurrent neural network to perform classification in this study. The system is also shown to be fully-automated, which implies the system can be deployed widely to all places easily. To validate our study, a series of experiments have been conducted with 120 speech samples, and the score in terms of the area under the receiver operating characteristic curve is as high as 0.838. ? 2019, The Author(s).
Other Subjects
aged; algorithm; Alzheimer disease; automated pattern recognition; caregiver; cognitive defect; computer assisted diagnosis; female; human; male; memory; middle aged; neuropsychological test; procedures; quality of life; receiver operating characteristic; reproducibility; speech; Aged; Algorithms; Alzheimer Disease; Caregivers; Cognitive Dysfunction; Diagnosis, Computer-Assisted; Female; Humans; Male; Memory; Middle Aged; Neural Networks, Computer; Neuropsychological Tests; Pattern Recognition, Automated; Quality of Life; Reproducibility of Results; ROC Curve; Speech
Type
journal article