Anxi: A Novel Natural Language Processing System for the Detection and Prevention of Anxiety Disorders
ISEF · 2023 Behavioral and Social Sciences Second Award
Overview
An estimated 31.1% of all adults will experience an anxiety disorder in their lifetime, yet mental health diagnostic and intervention tools remain largely inaccessible, unaffordable, and culturally stigmatized. To address this unmet need, an accessible and affordable diagnostic and assistive system was created through the development of two machine learning models and a mobile application. The first model, Anxi, is a fine-tuned version of GPT-4 that integrates core principles of cognitive behavioral therapy and mindfulness to identify and correct negative thought patterns related to anxiety. Using natural language processing, the second machine learning model analyzes conversations between users and Anxi to track anxiety levels over time with 96% accuracy. The system then stores this information in a retrievable database accessible to healthcare providers, facilitating more informed treatment plans, monitoring of patient progress, and data-driven decision-making. The mobile application graphically represents this tracked information, while periodically sending notifications encouraging users to check in and converse with Anxi, enabling users to monitor and manage their mental health. This system was deemed successful as it encompasses easily accessible diagnostic and assistive tools that have the potential to address other mental health disorders faced by over 450 million people worldwide.
Awards (1)
- Second Award of $2,000 $2,000
Competition history
- ISEF 2023
Resources
Related projects
ISEF · 2021
Anxiliary: A Novel Wearable Body Sensor Based Machine Learning System for the Detection, Tracking, and Intervention of Anxiety Disorders
ISEF · 2024
Projective Testing as Windows to the Mind: Unveiling Anxiety's Expression Through Artistic Mediums in Teenagers
ISEF · 2022
SuiSensor: A Novel, Low-Cost Machine Learning System for Real-Time Suicide Risk Identification and Treatment Optimization via Computational Linguistics
CWSF · 2026
Identification of Neurodevelopmental & Mental Health Conditions: An AI Approach to Reducing Barriers
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair