Autism detection for toddlers from behavioural indicators using classification techniques

Autism spectrum disorder (ASD) is a condition associated with impairments in communication, social, and repetitive behaviour; the degree of impairment varies between individuals with ASD. Since ASD has a substantial impact on the individual, caregivers, and family members due to the social and economic costs involved, early ASD screening becomes fundamental to enable faster access to healthcare resources. One of the important studied groups in ASD research is toddlers - detecting autistic traits at an early stage can help physicians develop treatment plans. This paper aims to improve the detection rate of ASD screening for toddlers using a data driven approach by identifying the impactful feature set related to ASD, and then processing these features using classification algorithms to accurately screen for ASD. To achieve the aim, a data driven framework consisting of feature selection and classification algorithms is proposed, and then implemented on a real dataset related to the ASD screening of toddlers. Empirical evaluations on the ASD screening dataset using different classification methods reveal that when support vector machine (SVM) or Naive Bayes are integrated with the proposed framework good predictive models are constructed for toddler ASD screening. These predictive models can be adopted by different medical staff and caregivers to replace scoring functions of conventional screening methods.