Aplicación de Machine Learning para la detección de patrones conductuales en Niños de 6 a 12 Años con TDAH

Abstract

Attention Deficit Hyperactivity Disorder (ADHD) profoundly affects children from 6 to 12 years old, generating challenges in their academic, social and emotional development. Traditional diagnostic methods, such as standardized questionnaires and clinical interviews, have been essential tools. However, they face limitations in dealing with large volumes of data and in providing a completely objective analysis of behavioral patterns. In this context, Machine Learning (ML) has emerged as an alternative that complements conventional approaches. This technology makes it possible to analyze data more efficiently, detecting complex patterns that might go unnoticed in traditional methods. This article explores how ML algorithms can contribute to improve the diagnosis of ADHD, offering faster and more accurate solutions that support specialists in their evaluations. The main objective of this study is to analyze how ML models can identify behaviors associated with ADHD, while addressing the challenges related to their implementation in clinical settings. By integrating these technological advances, we seek not only to optimize diagnostic procedures, but also to offer tangible benefits for both patients and their families. This interdisciplinary approach connects the fields of technology and health, setting a clear path toward future research that may revolutionize the diagnosis and management of ADHD.