Prediction of ADHD with Machine Learning: A Systematic Literature Review Abstract

Attention Deficit Hyperactivity Disorder (ADHD) affects approximately 13% of the child population; its diagnosis is based on clinical and behavioral assessments and psychometrics test results. Recently, Machine Learning (ML) has been used to detect various neuropsychiatric conditions, providing grea...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Quintero-López, Catalina, Gil Vera, Víctor Daniel, Cerpa Bernal, Rafael Mauricio, Herrera Martínez, Marcelo
Formato: Artículo revista
Lenguaje:Español
Publicado: Universidad Nacional de Córdoba 2024
Materias:
Acceso en línea:https://revistas.unc.edu.ar/index.php/racc/article/view/42221
Aporte de:
Descripción
Sumario:Attention Deficit Hyperactivity Disorder (ADHD) affects approximately 13% of the child population; its diagnosis is based on clinical and behavioral assessments and psychometrics test results. Recently, Machine Learning (ML) has been used to detect various neuropsychiatric conditions, providing greater diagnostic accuracy. The aim of this research was to conduct a systematic literature review (SLR) on the detection of ADHD in infants’ witch ML. Based on the PRISMA methodology, 30 publications were selected from Web of Science (WoS) and Scopus which met the eligibility criteria. This paper concludes that the most used technique for ADHD detection was Support Vector Machines, the best-performing model was obtained from psychometrics test. An accurate and early diagnosis of ADHD prevents long-term complications; emotional, academic, and social problems, as well as the development of an antisocial structure.