Year: 2025
Type: article
Abstract: The "Children ADHD Disease Detection Using Pose Estimation Techniques" project seeks to transform the early diagnosis of Attention Deficit Hyperactivity Disorder (ADHD) in children using sophisticated pose estimation algorithms. The novel method scrutinizes children's movement patterns and postures to detect possible symptoms of ADHD, providing a non-invasive and objective alternative to conventional assessment methods. ADHD, a neurodevelopmental condition that affects school performance and social function, stands to gain enormously from early detection and treatment. The project improves the validity and responsiveness of ADHD diagnoses through the use of PoseNet for pose estimation. The system records and analyzes the movement of the body during particular activities that are designed to trigger typical ADHD patterns of behavior. The project uses sensors, cameras, or depth sensors to record detailed movement data such as joint locations, angles, and time information. This information is used as input for a trained Support Vector Machine (SVM) model, which makes predictions about movement patterns of ADHD versus normal development. While this technology is promising, it is meant to augment and not replace thorough clinical evaluation, since ADHD is a complex disorder that needs to be approached in a holistic manner. Ethical issues, specifically around data privacy and the possibility of misuse, also need to be considered. This project is a major step forward in child mental health assessment. By bringing high-tech capabilities to the imperative of early and correct detection of ADHD, it can potentially enhance diagnostic precision, facilitate earlier intervention, and ultimately raise the quality of life in children with ADHD. Extensive testing and verification will be imperative to establish reliability, making this technique an important resource in ADHD assessment and care.
Language: English
Subfield: Psychiatry and Mental health
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4410271902