Abstract

ASD is a neurodevelopmental disorder that affects how people communicate, interact, and behave. It is not a single condition, but a spectrum of different symptoms and challenges that can vary from person to person. To diagnose ASD, clinicians and experts use various tests and observations, but these methods can have some drawbacks. They can be subjective, expensive, and time-consuming, and they may not work well for different cultures and regions. There is also no clear biological or genetic marker for ASD. ML is a type of artificial intelligence that can learn from data and make predictions or decisions without being programmed. ML can help with ASD diagnosis in different ways, such as screening, feature extraction, classification, and outcome prediction. Screening is the process of finding out who may have ASD and need more tests. Feature extraction is the process of getting useful information from the data, such as brain scans, speech patterns, or eye movements. Classification is the process of putting people into different groups or categories, such as ASD or non-ASD. Outcome prediction is the process of estimating the future situation or performance of people, such as their thinking skills or well-being. In this paper, we review the latest ML methods for ASD diagnosis and the challenges and limitations of these methods. We also talk about the ethical and social issues of using ML for ASD diagnosis and suggest some ideas for future research.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call