The project

BACKGROUND

Over the last few years, the linguistic productions of dementia patients have attracted growing attention, becoming an established research topic in the academic and medical community. In many types of dementia (e.g. Alzheimer's Disease and Frontotemporal Dementia),  there is strong evidence that language disruption is a common finding at the earliest stages and in full-blown pathology. Thus, the characterization of these impairments is playing an increasingly important role in the diagnosis, both in traditional clinical settings (i.e., neuropsychological assessment) and in cutting-edge experimental contexts. In particular, a rising number of studies show that verbal productions can be exploited as Digital Biomarkers. This technique revealed many advantages, including low cost, non-intrusive application, and time-effectiveness, when compared to traditional neuropsychological tests.

Previous findings demonstrated that acoustic features are the most reliable parameters for Dementia early identification through AI techniques. However, while lexical, syntactic, and pragmatic disturbances can be explained by the typical localization of brain atrophies (e.g., medial temporal lobe and hippocampus for Alzheimer's Disease) and linked to other cognitive alterations (e.g., episodic/semantic memory, executive functions), the relevance of voice abnormalities remains completely unexplored.

AKiD will build on past findings of the project partners and their experience in analyzing pathological and non-pathological speech to investigate the phonetic profile of patients with Dementia. We will enroll a balanced cohort of adult/elderly subjects living in Emilia Romagna: after the neuropsychological assessment, controlled and semi-spontaneous speech tasks will be administered to collect acoustic data and midsagittal ultrasound images of tongue shape and location through Ultra Tongue Imaging.

Open research issues

  1. Few studies (none for the Italian language) tackled a comprehensive description of the spectrographic segmental properties of speech in patients diagnosed with pre-clinical and clinical dementia.
  2. The articulatory substrate of acoustic alterations due to dementia has never been studied before instrumentally through UTI.
  3. The neurobiological underpinnings of these alterations remain largely unclear from a clinical perspective.

 

 

RESEARCH QUESTIONS

AKiD aims at exploring the phonetic characteristics of cognitive decline due to dementia through the following activity lines:

  • Research Question 1: Which acoustic parameters of speech are affected by Dementia?
    Objective 1: Describing voice alteration of the patients diagnosed with pre-clinical and clinical Dementia through the collection and spectrographic analysis of speech samples.
  • Research Question 2: What is the articulatory substrate of these acoustic alterations?
    Objective 2: Describing possible alteration of articulatory gesture of the patients diagnosed with pre-clinical and clinical Dementia through the dynamic analysis of midsagittal ultrasound images of tongue shape and location.

AKiD will drive progress in the knowledge of phonetic biomarkers of Cognitive Decline, a frontier research field at the national and international level.