Cognitive training personalization: an AI approach

MELINA VLADISAUSKAS; BELLOLI, LAOUEN MAYAL LOUAN; DIEGO FERNANDEZ SLEZAK; ANDREA P. GOLDIN

Congreso; XXXVI Reunión de la Sociedad Argentina de Investigación en Neurociencias (SAN); 2021

Sociedad Argentina de Investigación en Neurociencias (SAN)

Executive functions (EF) are a class of processes critical for purposeful goal-directed behavior. Cognitivetraining (i.e. the adequate stimulation of EF) has been studied and applied for the last 25 years in hugely diversebackgrounds. In spite of the accumulated evidence of its positive impact in cognition, there are still reports inthe literature that claim that the potential benefits of training are not generalizable. Recently, researchconsiders individual differences as one of the possible causes of these inconsistencies. Is it possible to build onetraining protocol that benefits everyone? Or is it time to stop considering individual differences as inevitableexperimental noise and, instead, use them as information that can guide us towards finding the best possiblestrategy for each person?In this study we use Machine Learning algorithms to identify and describe possible subgroups of individualsthat will (or will not) benefit from a certain stimulation. The algorithms were built using data from a cognitivetraining intervention (N=73 6 y.o.) run with a set of computerized games aimed at training and measuring EF(www.matemarote.org.ar).We present a Nearest Neighbors classifier that successfully predicts whether a subject will benefit or not froma fixed training approach based on his/her performance in previous cognitive tests. In the long term thesealgorithms will allow us to individualize training protocols in order to maximize the stimulation for each child.