Artificial Intelligence Enabled Personalized Assistive Tools To Enhance Education of Children With Neurodevelopmental Disorders

April 14, 2024

00:00

Personalized Learning

Mind and Brain Education                           

Mental Health

Children’s ability to learn effectively can be impacted by social and communication deficits and difficulties adapting to changes in their environment. To improve outcomes for children, it is important to provide timely and effective interventions. This review summarizes the range and effectiveness of AI-assisted tools, developed using machine learning models, which have been applied to address learning challenges in students with a range of neurodevelopmental disorders (NDDs). Our review summarizes the evidence that AI tools can be successfully used to improve social interaction and supportive education.

Neurodevelopmental Disorders Do Not Usually Appear Alone

Globally, childhood-onset mental disorders are becoming more prevalent, with a rate of 10–20%. NDDs are now recognized as a leading cause of morbidity in children, with a huge impact not only on the individual child but also on their families and society. Moreover, there is frequent overlap between NDDs and Mental Health Disorders (MHD). For example, between 30% and 50% of children with ADHD are reported to have a comorbid MHD, such as depression, and over 70% of children with ASD are reported to have a comorbid MHD, most commonly including anxiety (40%) and ADHD (30–40%). The complex web of comorbidities between NDDs and MHDs can contribute to the severity of learning disabilities in individual children and can further reduce the quality of life. This complex comorbidity can be associated with poorer long-term prognosis and has implications for tailoring treatments for individual children.

Most Learning Tools Have Been Created for ASD Students

The systematic review was conducted by analyzing the most relevant studies (2011-2021) on assistive tools developed to address learning disabilities. The study looked at different tools used to help students with ADHD, dyslexia, and ASD in their learning.

It found that most tools are made to help ASD students, with application-based tools being the most common. Robots and application-based tools are popular tools for students with ASD as they can help with social interactions and meet individual learning needs. More technology and AI tools are used for ASD compared to other learning disabilities, likely because ASD presents challenges in learning and social communication. Deep learning models are used to develop robots for ASD because ASD is different from person to person. 

Application-based tools are used to help students with dyslexia, offering personalized learning features. For ADHD, a mix of wearable devices, robots, and application-based tools is used, but not all tools are personalized to each student’s needs. The study suggests that AI tools should have personalized features to meet each student’s unique learning needs, as these needs vary greatly among individuals.

Safeguards Need To Be Put in Place To Protect Younger Students

Educational assistive technologies are commonly used with adolescents, therefore ethical concerns arise over privacy, data security, and informed consent. Safeguards need to be in place to ensure data cannot be hacked, and educators should ensure ethical considerations are in place before any student data is collected when an assistive tool is being used.

The AI-based tool is also able to perform data analysis rapidly and provide deeper insights

and hence is competent in offering real-time personalized recommendations to users.

While AI in cloud computing may generally lower costs, a well-trained staff needs to

be employed to operate the complex AI system which may incur some costs. The cloud

system would also require a continuous internet connection to work well; weak internet

access can impair the benefits of the cloud system.

Notable Quotes: 

“The model will then be able to predict the user’s learning needs accordingly

and provide personalized learning to suit the child’s learning needs.”

“This review highlights that despite being in its infancy stage, assisted tools have been proposed to address the learning needs and quality of life of children with the most common NDDs: ADHD, dyslexia, and ASD.”

“Inclusive approaches are recommended so that students with NDD can be included in mainstream schools whenever possible. However, mainstream classroom settings can worsen symptoms of ADHD, especially when children are expected to sit still, remain quiet and stay focused.”

Personal Takeaway: 

As a special education teacher, this study gives me a lot of hope. Adding AI to the toolbox of students with learning disorders can be a huge bonus but it should be implemented carefully. Reliance on the tool should be limited until the student is mature enough to realize that there are instances where they cannot rely on AI. Teacher involvement and training is also a big part of introducing AI to schools.—Shekufeh

Barua, P.D.; Vicnesh, J.; Gururajan, R.; Oh, S.L.; Palmer, E.; Azizan, M.M.; Kadri, N.A.; Acharya, U.R. Artificial Intelligence Enabled Personalized Assistive Tools to Enhance Education of Children with Neurodevelopmental Disorders—A Review. Int. J. Environ. Res. Public Health 2022, 19, 1192. https:// doi.org/10.3390/ijerph19031192