Autism Spectrum Disorder (ASD), according to DSM-5 in the American Psychiatric Association, is a neurodevelopmental disorder that includes deficits of social communication and social interaction with the presence of restricted and repetitive behaviors. Children with ASD have difficulties in joint attention and social reciprocity, using non-verbal and verbal behavior for communication. Due to these deficits, children with autism are often socially isolated. Researchers have emphasized the importance of early identification and early intervention to improve the level of functioning in language, communication, and well-being of children with autism. However, due to limited local assessment tools to diagnose these children, limited speech-language therapy services in rural areas, etc., these children do not get the rehabilitation they need until they get into compulsory schooling at the age of seven years old. Hence, efficient approaches towards early identification and intervention through speedy diagnostic procedures for ASD are required. In recent years, advanced technologies like machine learning have been used to analyze and investigate ASD to improve diagnostic accuracy, time, and quality without complexity. These machine learning methods include artificial neural networks, support vector machines, a priori algorithms, and decision trees, most of which have been applied to datasets connected with autism to construct predictive models. Meanwhile, the selection of features remains an essential task before developing a predictive model for ASD classification. This review mainly investigates and analyzes up-to-date studies on machine learning methods for feature selection and classification of ASD. We recommend methods to enhance machine learning’s speedy execution for processing complex data for conceptualization and implementation in ASD diagnostic research. This study can significantly benefit future research in autism using a machine learning approach for feature selection, classification, and processing imbalanced data.

Abstract:The economic burden of families with Autism Spectrum Disorders (ASD) children that are far beyond the needs of typical children causes physical and mental stress for their parents. The study aims to examine the economic burden of parents with ASD children in Malaysia. Calculation is made using a cost-loss approach due to ASD that include direct, indirect and developmental costs. Using convenient sampling method, a total of 245 parents have filled out questionnaires through online or hard copies. Development costs represent the highest cost of RM20,989.33, followed by medical direct costs RM8,378.73, RM5,033.57 for non-medical direct costs and RM963.99 for indirect costs. The total cost of financing an ASD child is RM35,365.62 a year. This is a huge and burdensome amount for parents. The findings of this study may assist responsible parties in the planning of effective service provision to suit the need of parents with ASD children in Malaysia.

No abstract

No abstract