Paper Title
Care Clarity: A Safe, AI-Assisted Decision Support System for Caregivers of Children with Autism Spectrum Disorder

Abstract
Autism Spectrum Disorder (ASD) affects 1 in 36 children in America and 1 in 100 worldwide, posing a huge and well documented burden on primary caregivers. Despite the enormity of this public health concern, the digital health space is dominated by unhelpful and generic solutions that do not cater to the information needs of the ASD community as determined by scientific research. Objective: The basis of justification for the paper is an overview of the latest literature (2022 and beyond) pertaining to the burden faced by caregivers, issues of access, and the newly discovered potential of Large Language Models in health support. In this paper, we introduce a web-based AI-assisted decision support system, particularly for caregivers of children suffering from ASD. Solution: The Care Clarity solution employs a multi-layer safety-filtered LLM pipeline, which is based on ASD-specific clinical literature, providing neurodiversity-affirming, evidence-based information in real-time. Results: A process of expert evaluation positions Care Clarity above other, more general AI chat bots, as well as traditional information, with regard to seven key aspects. Impact: Care Clarity represents a responsible, scalable, safety- first model for deploying AI in high-stakes caregiver support contexts, with significant Keywords - Autism Spectrum Disorder, ASD, caregiver technology, large language models, digital health, AI safety, neurodiversity, decision support, RAG pipeline, web application