On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis
The work presented here is part of a larger study to identify novel technologies and biomarkers for early Alzheimer disease (AD) detection and it focuses on evaluating the suitability of a new approach for early AD diagnosis by non-invasive methods. The purpose is to examine in a pilot study the pot...
Main Authors: | , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2013-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | http://www.mdpi.com/1424-8220/13/5/6730 |
_version_ | 1798035335193559040 |
---|---|
author | Unai Martinez de Lizardui Nora Barroso Miriam Ecay-Torres Pablo Martinez-Lage Marcos Faundez-Zanuy Aitzol Ezeiza Jordi Solé-Casals Harkaitz Egiraun Carlos Manuel Travieso Jesus-Bernardino Alonso Karmele López-de-Ipiña |
author_facet | Unai Martinez de Lizardui Nora Barroso Miriam Ecay-Torres Pablo Martinez-Lage Marcos Faundez-Zanuy Aitzol Ezeiza Jordi Solé-Casals Harkaitz Egiraun Carlos Manuel Travieso Jesus-Bernardino Alonso Karmele López-de-Ipiña |
author_sort | Unai Martinez de Lizardui |
collection | DOAJ |
description | The work presented here is part of a larger study to identify novel technologies and biomarkers for early Alzheimer disease (AD) detection and it focuses on evaluating the suitability of a new approach for early AD diagnosis by non-invasive methods. The purpose is to examine in a pilot study the potential of applying intelligent algorithms to speech features obtained from suspected patients in order to contribute to the improvement of diagnosis of AD and its degree of severity. In this sense, Artificial Neural Networks (ANN) have been used for the automatic classification of the two classes (AD and control subjects). Two human issues have been analyzed for feature selection: Spontaneous Speech and Emotional Response. Not only linear features but also non-linear ones, such as Fractal Dimension, have been explored. The approach is non invasive, low cost and without any side effects. Obtained experimental results were very satisfactory and promising for early diagnosis and classification of AD patients. |
first_indexed | 2024-04-11T20:56:48Z |
format | Article |
id | doaj.art-b9f08122347d4612818a9a4f633a7ff6 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T20:56:48Z |
publishDate | 2013-05-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-b9f08122347d4612818a9a4f633a7ff62022-12-22T04:03:40ZengMDPI AGSensors1424-82202013-05-011356730674510.3390/s130506730On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease DiagnosisUnai Martinez de LizarduiNora BarrosoMiriam Ecay-TorresPablo Martinez-LageMarcos Faundez-ZanuyAitzol EzeizaJordi Solé-CasalsHarkaitz EgiraunCarlos Manuel TraviesoJesus-Bernardino AlonsoKarmele López-de-IpiñaThe work presented here is part of a larger study to identify novel technologies and biomarkers for early Alzheimer disease (AD) detection and it focuses on evaluating the suitability of a new approach for early AD diagnosis by non-invasive methods. The purpose is to examine in a pilot study the potential of applying intelligent algorithms to speech features obtained from suspected patients in order to contribute to the improvement of diagnosis of AD and its degree of severity. In this sense, Artificial Neural Networks (ANN) have been used for the automatic classification of the two classes (AD and control subjects). Two human issues have been analyzed for feature selection: Spontaneous Speech and Emotional Response. Not only linear features but also non-linear ones, such as Fractal Dimension, have been explored. The approach is non invasive, low cost and without any side effects. Obtained experimental results were very satisfactory and promising for early diagnosis and classification of AD patients.http://www.mdpi.com/1424-8220/13/5/6730Alzheimer’s disease diagnosisspontaneous speechemotion recognitionmachine learningnon-invasive diagnostic techniquesdementia |
spellingShingle | Unai Martinez de Lizardui Nora Barroso Miriam Ecay-Torres Pablo Martinez-Lage Marcos Faundez-Zanuy Aitzol Ezeiza Jordi Solé-Casals Harkaitz Egiraun Carlos Manuel Travieso Jesus-Bernardino Alonso Karmele López-de-Ipiña On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis Sensors Alzheimer’s disease diagnosis spontaneous speech emotion recognition machine learning non-invasive diagnostic techniques dementia |
title | On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis |
title_full | On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis |
title_fullStr | On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis |
title_full_unstemmed | On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis |
title_short | On the Selection of Non-Invasive Methods Based on Speech Analysis Oriented to Automatic Alzheimer Disease Diagnosis |
title_sort | on the selection of non invasive methods based on speech analysis oriented to automatic alzheimer disease diagnosis |
topic | Alzheimer’s disease diagnosis spontaneous speech emotion recognition machine learning non-invasive diagnostic techniques dementia |
url | http://www.mdpi.com/1424-8220/13/5/6730 |
work_keys_str_mv | AT unaimartinezdelizardui ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT norabarroso ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT miriamecaytorres ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT pablomartinezlage ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT marcosfaundezzanuy ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT aitzolezeiza ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT jordisolecasals ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT harkaitzegiraun ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT carlosmanueltravieso ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT jesusbernardinoalonso ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis AT karmelelopezdeipina ontheselectionofnoninvasivemethodsbasedonspeechanalysisorientedtoautomaticalzheimerdiseasediagnosis |