Abstract

Disparities in autism diagnosis persist across racial, socioeconomic, and geographic lines, disproportionately affecting underserved communities. Historically, marginalized populations have been excluded from autism research and healthcare access, leading to delayed diagnoses, misdiagnoses, and limited early intervention opportunities. Factors such as implicit bias in traditional diagnostic methods, socioeconomic barriers, and lack of culturally competent healthcare services have further widened the autism diagnosis gap. Addressing these inequities requires innovative solutions that leverage digital health tools and AI-driven diagnostics to improve early detection and intervention in historically excluded populations. Emerging technologies, including machine learning-based autism screening, telehealth consultations, and mobile health applications, offer promising pathways to overcome structural barriers in autism diagnosis. AI-powered screening tools can enhance accuracy, efficiency, and accessibility, allowing for remote and cost-effective early detection in communities with limited access to specialized healthcare providers. Additionally, culturally tailored digital platforms can reduce bias in autism assessments and provide caregiver education and support, empowering families to seek timely interventions. However, challenges remain, including the digital divide, data privacy concerns, and the need for clinician training in AI-assisted diagnostics. This explores the intersection of historical healthcare exclusion and modern digital solutions, proposing a framework for equitable autism diagnosis and intervention. It highlights the potential of public-private partnerships, policy reforms, and community-based digital health initiatives to expand access to AI-driven autism screening. By integrating technology, policy, and culturally responsive care, digital inclusion can help close the autism diagnosis gap, ensuring that all children regardless of racial, economic, or geographic background receive timely and appropriate support. Future research should focus on refining AI models for diverse populations and scaling digital health interventions to bridge longstanding healthcare disparities in autism diagnosis and treatment.