Executive Functioning in Adults with Down Syndrome: Machine-Learning-Based Prediction of Inhibitory Capacity

Mario Fernando Jojoa-Acosta, Sara Signo-Miguel, Maria Begoña Garcia-Zapirain, Mercè Gimeno-Santos, Amaia Méndez-Zorrilla, Chandan J. Vaidya, Marta Molins-Sauri, Myriam Guerra-Balic and Olga Bruna-Rabassa
Additional contact information
Mario Fernando Jojoa-Acosta: eVIDA—Lab, Faculty of Engineering, Deusto University, 48007 Bilbao, Spain
Sara Signo-Miguel: Faculty of Psychology, Education and Sports Sciences Blanquerna, Ramon Llull University, 08022 Barcelona, Spain
Maria Begoña Garcia-Zapirain: eVIDA—Lab, Faculty of Engineering, Deusto University, 48007 Bilbao, Spain
Mercè Gimeno-Santos: Faculty of Psychology, Education and Sports Sciences Blanquerna, Ramon Llull University, 08022 Barcelona, Spain
Amaia Méndez-Zorrilla: eVIDA—Lab, Faculty of Engineering, Deusto University, 48007 Bilbao, Spain
Chandan J. Vaidya: Department of Psychology, Georgetown University, Washington, DC 20057, USA
Marta Molins-Sauri: Faculty of Psychology, Education and Sports Sciences Blanquerna, Ramon Llull University, 08022 Barcelona, Spain
Myriam Guerra-Balic: Faculty of Psychology, Education and Sports Sciences Blanquerna, Ramon Llull University, 08022 Barcelona, Spain
Olga Bruna-Rabassa: Faculty of Psychology, Education and Sports Sciences Blanquerna, Ramon Llull University, 08022 Barcelona, Spain

IJERPH, 2021, vol. 18, issue 20, 1-17

Abstract: The study of executive function decline in adults with Down syndrome (DS) is important, because it supports independent functioning in real-world settings. Inhibitory control is posited to be essential for self-regulation and adaptation to daily life activities. However, cognitive domains that most predict the capacity for inhibition in adults with DS have not been identified. The aim of this study was to identify cognitive domains that predict the capacity for inhibition, using novel data-driven techniques in a sample of adults with DS ( n = 188; 49.47% men; 33.6 ± 8.8 years old), with low and moderate levels of intellectual disability. Neuropsychological tests, including assessment of memory, attention, language, executive functions, and praxis, were submitted to Random Forest, support vector machine, and logistic regression algorithms for the purpose of predicting inhibition capacity, assessed with the Cats-and-Dogs test. Convergent results from the three algorithms show that the best predictors for inhibition capacity were constructive praxis, verbal memory, immediate memory, planning, and written verbal comprehension. These results suggest the minimum set of neuropsychological assessments and potential intervention targets for individuals with DS and ID, which may optimize potential for independent living.

Keywords: aging; artificial intelligence; cognition; Down syndrome; executive functions; feature selection; inhibition; machine learning; neuropsychology (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2021
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
https://www.mdpi.com/1660-4601/18/20/10785/pdf (application/pdf)
https://www.mdpi.com/1660-4601/18/20/10785/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:18:y:2021:i:20:p:10785-:d:656148

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().