Enhanced Autism Prediction using Hybrid Machine Learning Model

Title

Enhanced Autism Prediction using Hybrid Machine Learning Model

Creator

Bhavya, A.; Srivastava, Kamakshi; Jayapandian, N.

Description

Autism Spectrum Disorder (ASD) is a condition where individuals face challenges in neurological development and have verbal, non-verbal, learning and behavioral disorders. Even though this condition is identifiable in the first few years in the children's life, many remain undiagnosed until later. This leads to long term developmental issues and delayed interventions. This is what makes the early detection critical for improving development in children. Despite that, traditional diagnosis approaches like behavioral checklists and pre structured interviews rely on the clinician's expertise and are time consuming and have a risk of inconsistency. This study entails and addresses the above problem by proposing a machine learning based multi model to automate early detection in toddlers aged 12 to 36 months. In the initial stage, the traditional classification algorithms like Logistic Regression, SVM are evaluated with high accuracy, F1 score. Then, hybrid models are developed by combining Gradient Boosting as the anchor model with other high performing algorithms, to overcome the limitation of single classification models. These hybrid models help to overcome the limitations of the individual classifiers. Finally, the best-performing hybrid model is enhanced further by Hyperparameter tuning, Feature selection and Cross validation. The outcome of this research will be a hybrid model, combining machine learning algorithms with the best scores, ensuring high accuracy and low false positives. This aims to help in the detection of ASD in early stages in toddlers. 2025 IEEE.

Source

2025 IEEE 5th International Conference on ICT in Business Industry and Government, ICTBIG 2025;

Date

01-01-2025

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

Autism; Cross-validation; Deep Learning; Gradient Boosting; Machine Learning

Coverage

Bhavya A., CHRIST (Deemed to Be University), Department of CSE, India; Srivastava K., CHRIST (Deemed to Be University), Department of CSE, India; Jayapandian N., CHRIST (Deemed to Be University), Department of CSE, India

Rights

Restricted Access; Hardcopy may be available in the library

Relation

ISBN: 979-833157981-4;

Format

online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/ICTBIG68706.2025.11323994

https://www.scopus.com/pages/publications/105032907036?origin=resultslist