Media Release

Udupi, Apr 12: Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that affects a child's behaviour and social interactions. Early detection of ASD in young children is crucial for timely and improved treatment.

Students of Sri Madhwa Vadiraja Institute of Technology and Management (SMVITM) have developed the project to identify autism in toddlers using machine learning.

The aim of this project is to use machine learning techniques to identify autism risk based on questionnaires, rather than introducing an ASD detection system. This model uses the Lasso feature selection technique to select the most important questions to improve performance.

The selected features are then used to train the ensemble model using XGBoost, random forest, and gradient boosting methods, achieving an overall accuracy of 94.79%.

This application provides parents and caregivers with a user-friendly communication tool to assess potential autism symptoms in young children. This model is useful for screening and raising awareness of autism spectrum disorder.

This project was completed by the department of Computer Science and engineering students Ramya, Sharanya, ShreyaShetty, and Vaishnavi Bijoor, under the expert guidance of senior assistant professor Savita Shenoy.