Enhancing Adaptive Learning, Communication, and Therapeutic Accessibility through the Integration of Artificial Intelligence and Data-Driven Personalization in Digital Health Platforms for Students with Autism Spectrum Disorder

Shariful Haque; Md Samirul Islam; Md Iftakhayrul Islam; Md Saiful Islam; Rayhan Khan; Md Tanvir Rahman Tarafder; Nur Mohammad

doi:10.63332/joph.v5i8.3255

Authors

Shariful Haque School of Business, International American University, Los Angeles, CA 90010, USA
Md Samirul Islam School of Business, International American University, Los Angeles, CA 90010, USA
Md Iftakhayrul Islam School of Business, International American University, Los Angeles, CA 90010, USA
Md Saiful Islam College of Graduate and Professional Studies, Trine University, Angola, Indiana, USA
Rayhan Khan Department of Special Education and Counseling, California State University Los Angeles, Los Angeles, CA 90032, USA
Md Tanvir Rahman Tarafder College of Technology & Engineering, Westcliff University, Irvine, CA 92614, USA
Nur Mohammad College of Technology & Engineering, Westcliff University, Irvine, CA 92614, USA

DOI:

https://doi.org/10.63332/joph.v5i8.3255

Keywords:

Artificial Intelligence, Adaptive Learning, Autism Spectrum Disorder, Digital Health, Personalized Therapy, Communication Support, Machine Learning, Educational Technology

Abstract

Autism Spectrum Disorder (ASD) impacts millions worldwide, posing distinct obstacles in schooling, communication, and access to therapy. Conventional educational and therapeutic approaches, while sometimes helpful, frequently lack the adaptability and customization necessary to meet the varied needs of kids with ASD. This research tackles existing gaps by integrating advanced Artificial Intelligence (AI) techniques and data-driven personalization in digital health systems. This study presents a novel, AI-driven adaptive learning and treatment system specifically developed for kids with autism spectrum disorder (ASD). This research assesses the efficacy of AI-driven personalization in improving learning outcomes, communication skills, and therapeutic accessibility through the utilization of simulated experimental data. Adaptive machine learning algorithms, natural language processing, and reinforcement learning techniques were incorporated into digital platforms, resulting in tailored intervention models that dynamically adjust to the cognitive and communicative profiles of each learner. Results from the simulated experiments demonstrate substantial enhancements in tailored adaptive learning pathways, quantifiable progress in communication skills, and heightened therapeutic accessibility and engagement compared to conventional methods. The performance assessment of AI models reveals strong accuracy, responsiveness, and efficiency in customizing instructional and therapeutic content to meet individual learner requirements. This research enhances previous work by providing empirical insights and practical consequences, demonstrating how AI-driven devices can substantially improve educational experiences and treatment outcomes for kids with ASD. Future directions encompass empirical testing, ongoing enhancement of AI models, and additional investigation into scalable application options within educational and healthcare contexts.