A Study Integrating Vi Rtual Reality with Multi-Model Neuro-Sensing for Adhd’S Intelligent Attention Assessment(2/2)

Attention deficit hyperactivity disorder (ADHD) is a common neurobehavioral disorder in childhood. Due to the long-term negative effects on quality of life and the difficulty of spontaneous remission, early diagnosis and treatment are particularly important. The current assessment tools mainly include scales and neuropsychological tests. Scales are subjective and are not easy to quantify children's behaviors. Neuropsychological tests are usually performed by computers. There are still problems of ecological validity. Therefore, the diagnosis or evaluation of ADHD still faces many challenges. This study integrates VR technology with wearable neurobehavioral sensing technology, including brain waves, eye trajectory tracking, head rotation and limb movements, to develop an attention assessment system. Based on the Taiwanese children's classroom, a virtual classroom is developed. Tasks, in regard to selective attention, continuous attention, and executive function, are embedded into the virtual classroom. Machine learning methods are used to perform multi-modal analysis on the data of task performance (missing error rate, alternative error rate, response time), neural behavior (brain wave, eye trajectory tracking, head rotation, limb movement) and assessment scales (CONNERS, SNAP-IV, Weiss's) in order to establish an automated assessment/ diagnostic model for attention deficit and hyperactivity disorder. In addition, we will further explore the impact of a variety of distractions, including visual interference, auditory interference, smell interference, on the distraction of children's attention.