19
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      Speech Analysis by Natural Language Processing Techniques: A Possible Tool for Very Early Detection of Cognitive Decline?

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Background: The discovery of early, non-invasive biomarkers for the identification of “preclinical” or “pre-symptomatic” Alzheimer's disease and other dementias is a key issue in the field, especially for research purposes, the design of preventive clinical trials, and drafting population-based health care policies. Complex behaviors are natural candidates for this. In particular, recent studies have suggested that speech alterations might be one of the earliest signs of cognitive decline, frequently noticeable years before other cognitive deficits become apparent. Traditional neuropsychological language tests provide ambiguous results in this context. In contrast, the analysis of spoken language productions by Natural Language Processing (NLP) techniques can pinpoint language modifications in potential patients. This interdisciplinary study aimed at using NLP to identify early linguistic signs of cognitive decline in a population of elderly individuals.

          Methods: We enrolled 96 participants (age range 50–75): 48 healthy controls (CG) and 48 cognitively impaired participants: 16 participants with single domain amnestic Mild Cognitive Impairment (aMCI), 16 with multiple domain MCI (mdMCI) and 16 with early Dementia (eD). Each subject underwent a brief neuropsychological screening composed by MMSE, MoCA, GPCog, CDT, and verbal fluency (phonemic and semantic). The spontaneous speech during three tasks (describing a complex picture, a typical working day and recalling a last remembered dream) was then recorded, transcribed and annotated at various linguistic levels. A multidimensional parameter computation was performed by a quantitative analysis of spoken texts, computing rhythmic, acoustic, lexical, morpho-syntactic, and syntactic features.

          Results: Neuropsychological tests showed significant differences between controls and mdMCI, and between controls and eD participants; GPCog, MoCA, PF, and SF also discriminated between controls and aMCI. In the linguistic experiments, a number of features regarding lexical, acoustic and syntactic aspects were significant in differentiating between mdMCI, eD, and CG (non-parametric statistical analysis). Some features, mainly in the acoustic domain also discriminated between CG and aMCI.

          Conclusions: Linguistic features of spontaneous speech transcribed and analyzed by NLP techniques show significant differences between controls and pathological states (not only eD but also MCI) and seems to be a promising approach for the identification of preclinical stages of dementia. Long duration follow-up studies are needed to confirm this assumption.

          Related collections

          Most cited references57

          • Record: found
          • Abstract: not found
          • Article: not found

          The mini‐mental state examination: Normative study of an Italian random sample

            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Research priorities to reduce the global burden of dementia by 2025.

            At the First WHO Ministerial Conference on Global Action Against Dementia in March, 2015, 160 delegates, including representatives from 80 WHO Member States and four UN agencies, agreed on a call for action to reduce the global burden of dementia by fostering a collective effort to advance research. To drive this effort, we completed a globally representative research prioritisation exercise using an adapted version of the Child Health and Nutrition Research Initiative method. We elicited 863 research questions from 201 participants and consolidated these questions into 59 thematic research avenues, which were scored anonymously by 162 researchers and stakeholders from 39 countries according to five criteria. Six of the top ten research priorities were focused on prevention, identification, and reduction of dementia risk, and on delivery and quality of care for people with dementia and their carers. Other priorities related to diagnosis, biomarkers, treatment development, basic research into disease mechanisms, and public awareness and understanding of dementia. Research priorities identified by this systematic international process should be mapped onto the global dementia research landscape to identify crucial gaps and inform and motivate policy makers, funders, and researchers to support and conduct research to reduce the global burden of dementia. Efforts are needed by all stakeholders, including WHO, WHO Member States, and civil society, to continuously monitor research investments and progress, through international platforms such as a Global Dementia Observatory. With established research priorities, an opportunity now exists to translate the call for action into a global dementia action plan to reduce the global burden of dementia.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Language performance in Alzheimer's disease and mild cognitive impairment: a comparative review.

              Mild cognitive impairment (MCI) manifests as memory impairment in the absence of dementia and progresses to Alzheimer's disease (AD) at a rate of around 15% per annum, versus 1-2% in the general population. It thus constitutes a primary target for investigation of early markers of AD. Language deficits occur early in AD, and performance on verbal tasks is an important diagnostic criterion for both AD and MCI. We review language performance in MCI, compare these findings to those seen in AD, and identify the primary issues in understanding language performance in MCI and selecting tasks with diagnostic and prognostic value.
                Bookmark

                Author and article information

                Contributors
                Journal
                Front Aging Neurosci
                Front Aging Neurosci
                Front. Aging Neurosci.
                Frontiers in Aging Neuroscience
                Frontiers Media S.A.
                1663-4365
                13 November 2018
                2018
                : 10
                : 369
                Affiliations
                [1] 1Interdepartmental Centre for Industrial Research in Health Sciences and Technologies, University of Bologna , Bologna, Italy
                [2] 2Clinical Neuropsychology Unit, Arcispedale S. Maria Nuova di Reggio Emilia , Reggio Emilia, Italy
                [3] 3Department of Classical Philology and Italian Studies, University of Bologna , Bologna, Italy
                [4] 4Department of Pharmacy and Biotechnology, University of Bologna , Bologna, Italy
                Author notes

                Edited by: Muthuraman Muthuraman, Universität Mainz, Germany

                Reviewed by: Gabriel Gonzalez-Escamilla, Universitätsmedizin Mainz, Germany; Dumitru Ciolac, Nicolae Testemitanu State University of Medicine and Pharmacy, Moldova

                *Correspondence: Laura Calzà laura.calza@ 123456unibo.it

                †These authors have contributed equally to this work

                Article
                10.3389/fnagi.2018.00369
                6243042
                30483116
                1da812e6-36f8-4e0c-8d5a-b2fd6fa30e1b
                Copyright © 2018 Beltrami, Gagliardi, Rossini Favretti, Ghidoni, Tamburini and Calzà.

                This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

                History
                : 19 July 2018
                : 24 October 2018
                Page count
                Figures: 1, Tables: 3, Equations: 0, References: 80, Pages: 13, Words: 9500
                Categories
                Neuroscience
                Original Research

                Neurosciences
                cognitive decline,language,natural language processing,preclinical alzheimer,speech analysis,mild cognitive impairment

                Comments

                Comment on this article