Identification of Neurodevelopmental & Mental Health Conditions: An AI Approach to Reducing Barriers

Overview

Autism spectrum disorder (ASD) often co-occurs alongside attention deficit hyperactivity disorder (ADHD), obsessive-compulsive disorder (OCD), and generalized anxiety disorder (GAD), potentially complicating diagnosis and daily functioning. Additionally, many individuals face barriers obtaining formal assessments, leading to delayed or missed diagnoses. Existing online identification resources rely on static questionnaires and single-disorder screening, limiting their ability to capture overlapping traits, inconsistencies, and nuanced self-reporting. This project developed a chatbot interface that evaluates whether experiences align with diagnostic traits associated with these disorders. A large language model (LLM) processes open-ended responses to evaluate relevance, detect inconsistencies, and provide clarification when needed. The tool accurately detected inconsistencies (Phase 1: 94.54%; Phase 2: 87.50%) and autism, ADHD, OCD, and GAD (96.3% with simulated profiles and 92.86% with participant profiles). This tool demonstrates strong potential as an accessible screening resource for individuals considering a formal assessment.

Awards (1)

• Selected for CWSF 2026

Competition history

• CWSF 2026 Health & Wellness

Related projects

Closest projects by meaning, across every fair and year in the corpus.