A Systematic Review on Prognosis of Autism Using Machine Learning Techniques

Abstract

Quality of life (QoL) and QoL predictors have become crucial in the pandemic. Neurological anomalies are at the highest level of QoL threats. Autism is a multi-system disorder that causes behavioural, neurological, cognitive, and physical differences. Recent studies state that neurological disorders can result in dysfunction of brain or whole nervous system, which may cause other symptoms of Autism. The paper focuses on reviewing various Machine Learning techniques used for diagnosing Autism at an early age with the help of multiple datasets. The study of brain Magnetic Resonance Imaging (MRI) provides astute knowledge of brain structure that helps to study any minor to significant changes inside the brain that have emerged due to the disorder. Early diagnosis leads to a healthy life by getting timely treatment and training. "Early diagnosis of Autism Spectrum Disorder" is an objective and one of the prime goals of health establishments worldwide. The research paper aims to systematically review and find which machine learning algorithms are efficient for prognosis of Autism.

Advancing autism technology

“…AI and Machine Learning have largely been applied to the assessment of ASD. As a diagnostic tool, Machine Learning based on existing classification systems and large sets of diagnostic data has effectively been used to screen young children on the autism spectrum (Malviya & J, 2022; Siddiqui et al, 2021). Ben‐Sasson et al (2018) confirmed the utility of Machine Learning for effectively screening children for ASD based on their parents' social media posts.…”