ADHD Disease Detection in Children Using Pose Estimation Technique

In this paper we presented a pioneering initiative merging healthcare and technology to address the challenges surrounding the diagnosis and monitoring of Attention Deficit Hyperactivity Disorder (ADHD) in children.With ADHD affecting approximately 0.8-1.5% of the global population, its impact on academic, social, and health domains underscores the urgency for improved diagnostic approaches.Present methods reliant on manual monitoring are susceptible to errors and inefficiencies, necessitating more robust solutions.This project proposes leveraging machine learning and computer vision to automate the identification of ADHDrelated behaviours through body poses.By training Support Vector Machine (SVM) algorithms on datasets encompassing both typical and ADHD-associated poses, subtle distinctions can be analysed to detect abnormalities indicative of ADHD with enhanced accuracy.Such automation not only promises greater precision but also scalability and efficiency benefits over manual methods.By streamlining the diagnostic process, this approach enables earlier interventions, potentially improving outcomes for affected children.Furthermore, this interdisciplinary collaboration exemplifies the transformative potential of technology in healthcare, underscoring the importance of innovation and data-driven insights.Through this initiative, the project aims to establish a paradigm shift towards more efficient and effective diagnostic practices, ultimately enhancing the quality of life for children impacted by ADHD and their families on a global scale.