Classification of Schizophrenia Data Using Support Vector Machine (SVM)

Research output: Contribution to journalConference articlepeer-review

Schizophrenia is a severe and chronic mental disorder. This disorder is marked with disturbances in thoughts, perceptions, and behaviours. Due to these disturbances that can trigger Schizophrenics to commit suicide or attempt to do so, Schizophrenics have a lower life expectancy than the general population. Schizophrenia is also difficult to diagnose as there is no physical test to diagnose it yet and its symptoms are very similar to several other mental disorders. Using Northwestern University Schizophrenia Data, this research aims to distinguish people who are Schizophrenics and people who are not. The data consists of 392 observations and 65 variables that are demographic data and clinician-filled Scale for the Assessment of Positive and Negative Symptoms questionnaires. Classification method used is machine learning with Support Vector Machines (SVM). Simulations are done with different data and percentage of training data. In each simulation, accuracy is measured. Model performance validation and evaluation are done by averaging ten times Hold-Out Validations that were done. In conclusion, SVM successfully classified Schizophrenia data with final accuracy of 90.1%. Furthermore, SVM with linear kernel and Gaussian kernel reached an accuracy of 95.0% in at least one simulation in classifying Schizophrenia data.

Original languageEnglish
Article number012044
Book seriesJournal of Physics: Conference Series
Issue number1
Publication statusPublished - 4 Dec 2018
Event2nd Mathematics, Informatics, Science and Education International Conference, MISEIC 2018 - Surabaya, Indonesia
Duration: 21 Jul 2018 → …


Conference2nd Mathematics, Informatics, Science and Education International Conference, MISEIC 2018
Period21/07/2018 → …

Bibliographical note

Funding Information:
The authors would like to express appreciation for the support of data collection and sharing for this project, which were funded by NIMH grant 1R01 MH084803.

Publisher Copyright:
© Published under licence by IOP Publishing Ltd.

ID: 320796393