Date of Award
June 2018
Degree Type
Thesis
Degree Name
Master of Science (MS)
Department
Electrical Engineering and Computer Science
Advisor(s)
Reza Zafarani
Keywords
Autism, Developmental Disorders, Machine Learning, Parent-oriented reviews, Supervised Learning
Subject Categories
Engineering
Abstract
Early developmental disorders are common in children between the ages of 3 through 17. These developmental disorders begin at early ages and affect the day-to-day activities of children. These disorders also impact the growth and lifestyle of children. Most of the time these developmental disorders co-exist in children. The main focus of our research lies in Autism Spectrum Disorder, Attention-Deficit/Hyperactivity Disorder, Deletion syndrome (22q) and their co-occurrences.
Most child psychologists and pediatricians diagnose these disorders in children through parent-based surveys. Our research uses three different parent-based reports: (1) Autism Diagnostic Interview (ADI), (2) Behavioral Assessment Schedule for Children (BASC), and (3) Vineland Adaptive Behavior Scales. These reports are questionnaires filled by parents under the inspection of certified professionals. These examinations require substantial amount of time and yield results after at least 13 months of wait time; hence, there is a pressing need to expedite the disorder detection process. Here, we address this challenge by utilizing machine learning techniques.
We utilize Machine learning to parent-reviews to help understand the relevance and importance of parental assessments in diagnosing these disorders. Furthermore, we study the co-occurrence of these disorders and identify their indicators in parental-surveys using a variety of machine learning techniques. Our main objective is to determine whether one can accurately predict the occurrence of these disorders.
Access
Open Access
Recommended Citation
Sambatur, Siri Chandana, "Computational Analysis of Developmental Disorders in Children" (2018). Theses - ALL. 250.
https://surface.syr.edu/thesis/250