Artificial Intelligence and Computational Approaches for the Identification of Clinical Markers in Autism Spectrum Disorder (ASD)

Loading...
Thumbnail Image

Date

Journal Title

Journal ISSN

Volume Title

Publisher

Unuversity Setif 1 Ferhat Abbas . Faculty of Sciences

Abstract

This abstract discusses the integration of artificial intelligence (AI) and deep learning (DL) and machine laerning (ML) in the identification of clinical markers for Autism Spec-trum Disorder (ASD). It emphasizes the use of heterogeneous clinical, behavioral, and neuropsychological data combined with machine learning techniques to improve early diagnosis and patient stratification. Large-scale datasets and recent advances in data collection technologies have enabled the availability of complex ASD-related data, high-lighting the need for efficient computational approaches to extract meaningful patterns and biomarkers. The study highlights the importance of data preprocessing, including quality con-trol, normalization, and integration, to ensure the reliability and robustness of predictive models. Feature selection and dimensionality reduction techniques are applied to handle high-dimensional data, reduce noise, and identify the most discriminative clinical fea-tures associated with ASD. The performance of the proposed models is evaluated using standard metrics such as accuracy, precision and recall. This study develops a deep learning-based framework for identifying and predicting ASD-related clinical markers. The model incorporates advanced architectures, such as Convolutional Neural Networks (CNN) and other machine learning algorithms, and is trained on integrated multimodal datasets. To evaluate the effectiveness of the approach, different strategies are compared, including traditional feature selection methods and AI-driven automated feature extraction techniques. In conclusion, the experimental results demonstrate that AI-based models out-perform conventional statistical approaches in identifying relevant clinical markers and improving diagnostic accuracy. The ability of deep learning models to capture com-plex patterns and interactions within heterogeneous ASD data contributes significantly to their superior performance. These findings highlight the potential of AI in enhanc-ing early diagnosis, clinical decision-making, and personalized intervention strategies for Autism Spectrum Disorder.

Description

Citation

Endorsement

Review

Supplemented By

Referenced By