Abstract
Background: Various types of dementia and Mild Cognitive Impairment (MCI) are manifested as irregularities in human speech and language, which have proven to be strong predictors for the disease presence and progress ion. Therefore, automatic speech analytics provided by a mobile application may be a useful tool in providing additional indicators for assessment and detection of early stage dementia and MCI.
Method: 165 participants (subjects with subjective cognitive impairment (SCI), MCI patients, Alzheimer's disease (AD) and mixed dementia (MD) patients) were recorded with a mobile application while performing several short vocal cognitive tasks during a regular consultation. These tasks included verbal fluency, picture description, counting down and a free speech task. The voice recordings were processed in two steps: in the first step, vocal markers were extracted using speech signal processing techniques; in the second, the vocal markers were tested to assess their ‘power' to distinguish between SCI, MCI, AD and MD. The second step included training automatic classifiers for detecting MCI and AD, based on machine learning methods, and testing the detection accuracy.
Results: The fluency and free speech tasks obtain the highest accuracy rates of classifying AD vs. MD vs. MCI vs. SCI. Using the data, we demonstrated classification accuracy as follows: SCI vs. AD = 92% accuracy; SCI vs. MD = 92% accuracy; SCI vs. MCI = 86% accuracy and MCI vs. AD = 86%.
Conclusions: Our results indicate the potential value of vocal analytics and the use of a mobile application for accurate automatic differentiation between SCI, MCI and AD. This tool can provide the clinician with meaningful information for assessment and monitoring of people with MCI and AD based on a non-invasive, simple and low-cost method.
Keywords: Alzheimer, dementia, assessment, MCI, speech, audio analysis, machine learning, algorithm.
Current Alzheimer Research
Title:Use of Speech Analyses within a Mobile Application for the Assessment of Cognitive Impairment in Elderly People
Volume: 15 Issue: 2
Author(s): Alexandra Konig*, Aharon Satt, Alex Sorin, Ran Hoory, Alexandre Derreumaux, Renaud David and Phillippe H. Robert
Affiliation:
- EA CoBTeK, University of Nice Sophia Antipolis, Nice,France
Keywords: Alzheimer, dementia, assessment, MCI, speech, audio analysis, machine learning, algorithm.
Abstract: Background: Various types of dementia and Mild Cognitive Impairment (MCI) are manifested as irregularities in human speech and language, which have proven to be strong predictors for the disease presence and progress ion. Therefore, automatic speech analytics provided by a mobile application may be a useful tool in providing additional indicators for assessment and detection of early stage dementia and MCI.
Method: 165 participants (subjects with subjective cognitive impairment (SCI), MCI patients, Alzheimer's disease (AD) and mixed dementia (MD) patients) were recorded with a mobile application while performing several short vocal cognitive tasks during a regular consultation. These tasks included verbal fluency, picture description, counting down and a free speech task. The voice recordings were processed in two steps: in the first step, vocal markers were extracted using speech signal processing techniques; in the second, the vocal markers were tested to assess their ‘power' to distinguish between SCI, MCI, AD and MD. The second step included training automatic classifiers for detecting MCI and AD, based on machine learning methods, and testing the detection accuracy.
Results: The fluency and free speech tasks obtain the highest accuracy rates of classifying AD vs. MD vs. MCI vs. SCI. Using the data, we demonstrated classification accuracy as follows: SCI vs. AD = 92% accuracy; SCI vs. MD = 92% accuracy; SCI vs. MCI = 86% accuracy and MCI vs. AD = 86%.
Conclusions: Our results indicate the potential value of vocal analytics and the use of a mobile application for accurate automatic differentiation between SCI, MCI and AD. This tool can provide the clinician with meaningful information for assessment and monitoring of people with MCI and AD based on a non-invasive, simple and low-cost method.
Export Options
About this article
Cite this article as:
Konig Alexandra*, Satt Aharon, Sorin Alex, Hoory Ran, Derreumaux Alexandre , David Renaud and Robert H. Phillippe, Use of Speech Analyses within a Mobile Application for the Assessment of Cognitive Impairment in Elderly People, Current Alzheimer Research 2018; 15 (2) . https://dx.doi.org/10.2174/1567205014666170829111942
DOI https://dx.doi.org/10.2174/1567205014666170829111942 |
Print ISSN 1567-2050 |
Publisher Name Bentham Science Publisher |
Online ISSN 1875-5828 |
Call for Papers in Thematic Issues
New Advances in the Prevention, Diagnosis, Treatment, and Rehabilitation of Alzheimer's Disease
Aims and Scope: Introduction: Alzheimer's disease (AD) poses a significant global health challenge, with an increasing prevalence that demands concerted efforts to advance our understanding and strategies for prevention, diagnosis, treatment, and rehabilitation. This thematic issue aims to bring together cutting-edge research and innovative approaches from multidisciplinary perspectives to address ...read more
Current updates on the Role of Neuroinflammation in Neurodegenerative Disorders
Neuroinflammation is an invariable hallmark of chronic and acute neurodegenerative disorders and has long been considered a potential drug target for Alzheimer?s disease (AD) and dementia. Significant evidence of inflammatory processes as a feature of AD is provided by the presence of inflammatory markers in plasma, CSF and postmortem brain ...read more
Deep Learning for Advancing Alzheimer's Disease Research
Alzheimer's disease (AD) poses a significant global health challenge, with an increasing number of individuals affected yearly. Deep learning, a subfield of artificial intelligence, has shown immense potential in various domains, including healthcare. This thematic issue of Current Alzheimer Research explores the application of deep learning techniques in advancing our ...read more
Diagnostic and therapeutic biomarkers of dementia
Dementia affects 18 million people worldwide. Dementia is a syndrome of symptoms caused by brain disease, usually chronic or progressive, clinically characterized by multiple impairments of higher cortical functions such as memory, thinking, orientation, and learning. In addition, in the course of dementia, cognitive deficits are observed, which often hinder ...read more
- Author Guidelines
- Graphical Abstracts
- Fabricating and Stating False Information
- Research Misconduct
- Post Publication Discussions and Corrections
- Publishing Ethics and Rectitude
- Increase Visibility of Your Article
- Archiving Policies
- Peer Review Workflow
- Order Your Article Before Print
- Promote Your Article
- Manuscript Transfer Facility
- Editorial Policies
- Allegations from Whistleblowers
- Announcements
Related Articles
-
Discovery of Chromen-7-yl Furan-2-Carboxylate as a Potent and Selective Factor XIa Inhibitor
Cardiovascular & Hematological Agents in Medicinal Chemistry Bioactivity Guided Isolation of Quercetin as Anxiolytic Compound from Elaeocarpus ganitrus Beads
The Natural Products Journal Genetic Editing and Pharmacogenetics in Current And Future Therapy Of Neurocognitive Disorders
Current Alzheimer Research Factors of Rapid Cognitive Decline in Late Onset Alzheimer's Disease
Current Aging Science NGA- A Novel Hypothetical Drug Model: Combinatorial Approach to Multifactorial Alzheimer's Disease
Current Drug Discovery Technologies NAP Protects against Tau Hyperphosphorylation Through GSK3
Current Pharmaceutical Design Adolescent HIV-1 Transgenic Rats: Evidence for Dopaminergic Alterations in Behavior and Neurochemistry Revealed by Methamphetamine Challenge
Current HIV Research Nitric Oxide-Derived Oxidants with a Focus on Peroxynitrite: Molecular Targets,Cellular Responses and Therapeutic Implications
Current Pharmaceutical Design Stem Cells: In Sickness and in Health
Current Stem Cell Research & Therapy The General Practitioners Role in Promoting Physical Activity to Older Adults: A Review Based on Program Theory
Current Aging Science Hyponatraemia Associated with Trimethoprim Use
Current Drug Safety The Adult Patient with Eisenmenger Syndrome: A Medical Update after Dana Point Part II: Medical Treatment - Study Results
Current Cardiology Reviews Osteoprotegerin in Cardiovascular Disease: Ally or Enemy?
Current Pharmaceutical Design Triggering Receptor Expressed on Myeloid Cells (TREM) Family and the Application of Its Antagonists
Recent Patents on Anti-Infective Drug Discovery Neuroimaging Studies of Substance Abuse in Schizophrenia
Current Psychiatry Reviews The Therapeutic Potential of Melatonin in Neurological Disorders
Recent Patents on Endocrine, Metabolic & Immune Drug Discovery Nano-Systems for Advanced Therapeutics and Diagnosis of Atherosclerosis
Current Pharmaceutical Design Prodrugs and Endogenous Transporters: Are They Suitable Tools for Drug Targeting into the Central Nervous System?
Current Pharmaceutical Design How Would Composite Traditional Chinese Medicine Protect the Brain – An Example of the Composite Formula “Pien Tze Huang”
Current Medicinal Chemistry AβPP-induced UPR Transcriptomic Signature of Glial Cells to Oxidative Stress as an Adaptive Mechanism to Preserve Cell Function and Survival
Current Alzheimer Research