A hybrid conceptual model using statistical and linguistic methods for pre-screening memory through language and cognition

This work is multidisciplinary (informatics, Artificial Intelligence, linguistics, and cognitive psychology) and transversal (health needs of a social nature inspired by technology), and its objective is the pre-diagnosis of people with memory problems. Language and cognitive assessment will be carr...

Descripción completa

Detalles Bibliográficos
Autores: Panesar, Kulvinder, Pérez Cabello de Alba, María Beatriz
Tipo de recurso: capítulo de libro
Fecha de publicación:2024
País:España
Institución:Universidad Nacional de Educación a Distancia
Repositorio:e-spacio. Repositorio Institucional de la UNED
Idioma:inglés
OAI Identifier:oai:e-spacio.uned.es:20.500.14468/24506
Acceso en línea:https://hdl.handle.net/20.500.14468/24506
Access Level:acceso abierto
Palabra clave:55 Historia::5505 Ciencias auxiliares de la historia::5505.10 Filología
language production and comprehension
pre-screening model
Role and Reference Grammar
speech assessment
natural language processing
Descripción
Sumario:This work is multidisciplinary (informatics, Artificial Intelligence, linguistics, and cognitive psychology) and transversal (health needs of a social nature inspired by technology), and its objective is the pre-diagnosis of people with memory problems. Language and cognitive assessment will be carried out via language production and comprehension of speech as a pre-diagnosis of dementia. Dementia and associated conditions are a global health problem supported by diverse expert groups, communities, research, and innovation (Alzheimer 2018, 2021, 2022). To take a small step in proactive early detection, we will employ a language and cognition assessment model supported by the DementiaBank multimedia database. This will provide results in terms of indicators of any potential problems with language production and cognition, as well as recommendations for the participant and carer, and as a precursor to other clinical tests for the diagnosis of dementia. The intervention will help to understand the person’s cognitive status and the early onset dementia and support the planning of healthcare provision. We will create a hybrid solution that contributes to research related to Natural Language Understanding, AI healthcare applications, and insights into cognitive impairment assessment. In this paper we present a schematic visual representation of a hybrid modular conceptual framework of a conversational agent.