Linguistic biomarkers of dementia in Italian patients living in Lombardy: insights from NLP analysis

Abstract

Nowadays, dementia poses a major challenge for healthcare services, with consequences on both the economic and the organizational front. The number of people affected by this disease is steadily increasing, and existing pharmacological and psycho-social therapies only aim to slow its progression. Therefore, a timely diagnosis is crucial for early intervention. For this reason, researchers from different disciplines are trying to find the “biomarkers” of dementia to obtain a detailed profiling of this disease and its etiology. In particular, great attention has been directed towards language, as it is one of the first cognitive domains affected by the pathology. The new frontier in the analysis of spoken language productions is the employment of Natural Language Processing (NLP) techniques and Artificial Intelligence (AI), as they enable an ecological and non-intrusive detection of dementia.

This study aims at analyzing the speech of elderly individuals diagnosed with dementia and living in Lombardy (Italy) exploiting NLP techniques. A cohort of 8 participants was enrolled, consisting of 4 patients affected by dementia (i. e., Alzheimer’s disease or mixed dementia) and 4 healthy controls matched by age, level of education, and sex. Participants’ selection was made on four neuropsychological tests (i. e., MMSE – Mini-Mental State Examination, MoCA – Montreal Cognitive Assessment, phonemic and semantic fluences). The speech samples were collected through three elicitation tasks and subsequently manually transcribed using the ELAN software. A multidimensional parameter analysis was performed on the corpus obtained taking into consideration a set of 151 linguistic features. Finally, a statistical analysis was performed by comparing the pathological group and the control group. Results demonstrate the efficacy of computational linguistic analysis in differentiating one group from another. Moreover, given the peculiar sociolinguistic situation in Italy, the study confirms the importance of investigating differences related to diatopic variation in clinical populations.