Publication Date

Fall 2015

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science


Data Analytics and Machine learning in healthcare are one of the most emerging and needed fields in current time. Also, a lot of research has been performed and is still being done in this field. In healthcare, gone are those days when only doctor examines and patient listens. Now doctor has a lot of technologies which can assist him and help in accurately diagnosing the disease with which his patient is suffering. The backbone of such technologies is data analytics and machine learning where we can make out a lot of inferences from tons of patients‟ data already available. This project aims at performing research and implementation of big data and machine learning techniques on the data related to the patients suffering from the disease called Autism. Autism is a neural disorder disease characterized by impaired social communication, verbal and non-verbal interaction, restrictive and repetitive behavior [4]. Autism is majorly noticed in children under or about the age of two years. One very important thing to be observed here is that autism is highly heritable and the cause includes both environmental factors and genetic susceptibility. Hence it is very important to have such data which contains details of patients including their symptoms, lab test data, history, vaccination details etc. which gives specific details of patients and their history. The project ultimately aims at training the data model with the set of training data and then testing and evaluating the data model using the test data. In this way, it should be a research and solution for implementing machine learning to detect and diagnose autism.