On the analysis of speech and disfluencies for automatic detection of Mild Cognitive Impairment
- PDF / 1,990,133 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 58 Downloads / 237 Views
(0123456789().,-volV)(0123456789().,-volV)
S.I. : ADVANCES IN BIO-INSPIRED INTELLIGENT SYSTEMS
On the analysis of speech and disfluencies for automatic detection of Mild Cognitive Impairment K. Lo´pez-de-Ipin˜a1 • U. Martinez-de-Lizarduy1 • P. M. Calvo1 • B. Beitia1 • J. Garcı´a-Melero1 • E. Ferna´ndez1 M. Ecay-Torres2 • M. Faundez-Zanuy3 • P. Sanz4
•
Received: 15 January 2018 / Accepted: 18 April 2018 The Author(s) 2018
Abstract Alzheimer’s disease is characterized by a progressive and irreversible cognitive deterioration. In a previous stage, the socalled Mild Cognitive Impairment or cognitive loss appears. Nevertheless, this previous stage does not seem sufficiently severe to interfere in independent abilities of daily life, so it is usually diagnosed inappropriately. Thus, its detection is a crucial challenge to be addressed by medical specialists. This paper presents a novel proposal for such early diagnosis based on automatic analysis of speech and disfluencies, and Deep Learning methodologies. The proposed tools could be useful for supporting Mild Cognitive Impairment diagnosis. The Deep Learning approach includes Convolutional Neural Networks and nonlinear multifeature modeling. Additionally, an automatic hybrid methodology is used in order to select the most relevant features by means of nonparametric Mann–Whitney U test and Support Vector Machine Attribute evaluation. Keywords Mild Cognitive Impairment Automatic Speech Analysis Deep Learning Convolutional Neural Networks Nonlinear features Disfluencies
1 Introduction Alzheimer’s disease (AD) is characterized by a progressive and irreversible cognitive deterioration, which includes memory loss and impairments in emotion, language, and judgment, along with other cognitive deficits and symptoms in behavior. Its prevalence keeps increasing mainly
among the elderly, and as highlighted by the last World Alzheimer Reports, AD is becoming epidemic as 900 million people can be regarded as the world’s elderly population, living most of them in developed countries [1]. Therefore, an early and accurate diagnosis of AD helps patients and relatives to plan the future and offers the best possibilities that symptoms could be treated.
& K. Lo´pez-de-Ipin˜a [email protected]
M. Faundez-Zanuy [email protected]
U. Martinez-de-Lizarduy [email protected] P. M. Calvo [email protected]
P. Sanz [email protected] 1
Faculty of Engineering, Universidad del Paı´s Vasco/Euskal Herriko Unibertsitatea (UPV/EHU), 20018 Donostia-San Sebastian, Spain
2
Fundacio´n CITA Alzheimer, 20009 Donostia, Spain
J. Garcı´a-Melero [email protected]
3
Tecnocampus Mataro´, Escola Superior Polite`cnica de Mataro´ (UPF), 08302 Mataro´, Spain
E. Ferna´ndez [email protected]
4
Neurology Department, Mataro Hospital, 08302 Mataro´, Spain
B. Beitia [email protected]
M. Ecay-Torres [email protected]
123
Neural Computing and Applications
In an early stage, a previous cognitive loss or Mild Cognitive Impairment (MCI) appears. Neve
Data Loading...
