V-038 | Online assessment of individual differences on executive function with the cursor trajectories in a Trail-Making Test

Cognition, Behavior, and Memory
Author: Gianluca Capelo | Email: gianluca.capelo@gmail.com

Gianluca Capelo^1°2°, Gustavo E Juantorena^1°,Agustín Petroni^3°, Juan E Kamienkowski^1°2°4°

^1° Laboratorio de Inteligencia Artificial Aplicada, Instituto de Ciencias de la Computación, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires – CONICET, Argentina
^2° Departamento de Computación, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires, Argentina
^3° University of Gothenburg, Sweden
^4° Maestría de Explotación de Datos y Descubrimiento del Conocimiento, Facultad de Ciencias Exactas y Naturales – Facultad de Ingeniería, Universidad de Buenos Aires, Argentina

The Trail-Making Test (TMT) is a widely used neuropsychological assessment designed to evaluate executive functions, which are critical for complex cognitive processes. Traditionally administered via pencil and paper, the TMT exhibits high sensitivity but low specificity. To cope with this deficit, we have implemented a digital version of the TMT, and validated with other standardized tests to measure different executive functions, such as the Change Detection Task for visual working memory, and Go/No-Go and Stop-Signal Tasks for inhibitory control. Moreover, to make these experiments accessible to different populations, a web platform (https://datapruebas.org/) was developed, where we collected data from over 300 participants performing the four tasks. This data is being analyzed to extract attributes that accurately represent performance on the TMT, based on the trajectory of the cursor. These attributes will be used to predict the executive function capabilities, such as working memory or inhibitory control, measured by the other three tasks.

The aim of this project is to predict, through a comprehensive analysis of a complex task like the TMT, the individual differences in executive functions present in the general population, with the goal of employing this methodology in the future for the early detection of neurodegenerative diseases associated with executive functions, such as Alzheimer’s and other related dementias.