Modeling the Contribution of Genetic Variation to Cognitive Gains Following Training with a Machine Learning Approach. Issue 4 (5th October 2022)

• Record Type: Journal Article
• Authors: Musso, Mariel F.; Cómbita, Lina M.; Cascallar, Eduardo C.; Rueda, M. Rosario
• Other Names: Grigorenko Elena guestEditor.; van Bergen Elsje guestEditor.
• Is Part Of: Mind, brain and education. Volume 16:Issue 4(2022)
• Page Start: 300
• Page End: 317
• Publication Date: 2022-10-05
• Subjects: Cognitive learning -- Periodicals; Education -- Research -- Periodicals; Developmental psychobiology -- Periodicals; Cognitive neuroscience -- Periodicals; Cognitive science -- Periodicals; Apprentissage cognitif -- Périodiques; Éducation -- Recherche -- Périodiques; Psychobiologie du développement -- Périodiques; Neurosciences cognitives -- Périodiques; Sciences cognitives -- Périodiques; 612.8233
• DOI: 10.1111/mbe.12336
• Languages: English
• ISSNs: 1751-2271

Abstract

Abstract: The objective of this research was to develop robust predictive models of the gains in working memory (WM) and fluid intelligence (Gf) following executive attention training in children, using genetic markers, gender, and age variables. We explore the influence of genetic variables on individual differences in susceptibility to intervention. Sixty‐six children (males: 54.2%) aged 50.9–75.9 months participated in a four‐weeks computerized training program. Information on genes involved in the regulation of dopamine, serotonin, norepinephrine, and acetylcholine was collected. The standardized pre‐ to post‐training gains of two dependent measures were considered: WM Span backwards condition (WISC‐III) and the IQ‐f factor from the Kaufman Brief Intelligence Test (K‐BIT). A machine‐learning methodology was implemented utilizing multilayer perceptron artificial neural networks (ANN) with a backpropagation algorithm. Both ANN models reached high overall accuracy in their predictive classification. Variations in genes involved in dopamine and norepinephrine neurotransmission affect children's susceptibility to benefit from executive attention training, a pattern that is consistent with previous studies. LAY ABSTRACT: The goal of this study was to use genetic markers related to the regulation of neurotransmitters associated with cognitive control and attention, to achieve an accurate predictive classification of cognitive gain outcomes following an attentional training module in children. We developed machine learning models including the genetic markers, gender and age, with data from a sample of 66 children, both genders, ages 4‐6 years old, who participated in a four‐week computerized training program. Results suggest that we can use a machine learning approach to identify, with high accuracy, which children would benefit from a specific cognitive training program increasing their fluid intelligence and/or working memory capacity, based only on the patterns of information from the variables in the study. These results have important implications for the design of targeted and early interventions during children's cognitive development and they highlight the importance of genetic information in the understanding of cognitive performance.