Gloria Gagliardi

Speech analysis by Natural Language Processing techniques: a possible tool for very early detection of cognitive decline?

Background: The discovery of early, non-invasive biomarkers for the identification of “preclinical” or “pre-symptomatic” Alzheimers 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.

LINGUISTIC MARKERS DURING SPONTANEOUS SPEECH FOR DETECTING MILD COGNITIVE IMPAIRMENT

Background:Novel approaches for the identification of “preclinical” or “pre-symptomatic” Alzheimer’s disease and other dementia are a key issue in the field, also in view of early biomarkers discovery. Recent studies showed that discourse alterations may be one of the earliest signs of the pathology, frequently measurable years before other cognitive deficits become apparent. Traditional neuropsychological tests fail to identify these changes. In contrast, the analysis of spoken language productions by Natural language processing (NLP) techniques can ecologically pinpoint language modifications in potential patients. This interdisciplinary study aimed at using NLP to identify early linguistic signs of cognitive decline in the elderly.Methods:We enrolled 96 subjects (age range 50-75): 48 healthy controls and 48 impaired subjects: 16 subjects with single domain amnestic Mild Cognitive Impairment (a-MCI), 16 with multiple domain MCI (md-MCI) 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 (complex picture; a typical working day; the 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 67 rhythmic, acoustic, lexical, morpho-syntactic and syntactic features. Results:Neuropsychological tests showed significant differences between controls and md-MCI, and between controls and eD subjects (p<0,01); MoCA, phonemic fluency and GPCog discriminated between controls and a-MCI (p<0,05) while MMSE, CDT and semantic fluency didn’t differentiate between the two groups (p>0,05). In the linguistic experiments, a number of features regarding lexical, acoustic and syntactic aspects were significant (p<0.05 using the Kolmogorov-Smirnov test) in differentiating between all the considered subject groups. Conclusions: Linguistic features of spontaneous discourse transcribed and analyzed by NLP techniques show significant differences between controls and pathological states, 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. Supported by OPLON, MIUR (L.C.).

Strumenti di screening linguistico per l’identificazione precoce della fragilità cognitiva

This paper presents the preliminary results of the OPLON project, co-funded by the Ministry of Education as part of the contract “Smart Cities and Communities and Social Innovation”. It aimed at identifying early linguistic symptoms of cognitive decline in the elderly. This pilot study was conducted on a corpus composed of spontaneous speech sample collected from 20 subjects, who underwent a neuropsychological screening for visuo-spatial abilities, memory, language, executive functions and attention. A rich set of linguistic features was extracted from the digitalized utterances (at phonetic, suprasegmental, lexical, morphological and syntactic levels) and the statistical significance in pinpointing the pathological process was measured. Our results, far from being complete, show remarkable trends for what concerns both the linguistic traits selection and the automatic classifiers building.