Open	Ananya Kaligal is a 3rd Year Student at the RV University, Bengaluru, India.

Poster Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by a range of challenges in social interaction, communication, and behavior. Early and precise diagnosis is crucial for effective intervention and support. This study leverages machine learning techniques to analyze Q-chat data, aiming to enhance ASD diagnosis and early intervention. The methodology involves implementing ETL pipelines to preprocess raw data, performing feature selection to categorize Q-chat questions, and visualizing the distribution of autistic and control subjects across different age groups to address class imbalances. Predictive models, including Logistic Regression, Random Forest, and Support Vector Machines (SVM), are constructed and evaluated using various performance metrics such as Confusion Matrix, Balanced Accuracy (Bacc), MCC, and Precision-Recall Curves. SHAP values are calculated and visualized to interpret the impact of different features on model predictions. Additionally, ROXIE Queries are utilized to deliver tailored advice based on user responses to Q-chat questions, providing actionable recommendations for addressing specific ASD-related concerns.

Presentation

In this Video Recording, Ananya provides a tour and explanation of her poster content.

Enhancing Early Detection and Visualization of Autism Spectrum Disorder:

Click on the poster for a larger image.

Open