NeuroRoad: An AI-Assisted Role-Based Learning Management System for Neurodivergent Education

Abstract

Neurodivergent learners, which includes indi- viduals with Autism Spectrum Disorder (ASD),Attention- Deficit/Hyperactivity Disorder (ADHD) and Dyslexia, require personalized instructions that go beyond the capabilities of existing learning management systems (LMS). Most already existing platforms give more importance to personalized content delivery and assessment, offering limited support for behavioral monitoring, clinical collaboration, and long-term intervention evaluation. This paper presents NeuroRoad, an AI assisted, role-based learning management system developed to facilitate personalized education and coordinated therapeutic workflows for neurodivergent students.
The platform supports structured collaboration among students, parents, psychologists, and administrators through clearly defined roles and access controls. NeuroRoad integrates condition-specific assessments, adaptive learning exercises, struc- tured behavioral observations, intervention planning, and con- sultation scheduling within a unified environment. AI assisted analytics are employed to identify learning trends and behavioral patterns, providing interpretable insights while ensuring that all educational and clinical decisions remain under professional human supervision. The system is implemented using a scalable monorepo architecture with a modern web frontend, a mod- ular backend, and a relational database for longitudinal data management. NeuroRoad demonstrates how ethically guided AI integration and collaborative system design can enhance person- alized learning and intervention effectiveness in neurodivergent education.