The 10th annual MLSP competition: Second place

The goal of the MLSP 2014 Classification Challenge was to automatically detect subjects with schizophrenia and schizoaffective disorder based on multimodal features derived from the magnetic resonance imaging (MRI) data. The patients with age range of 18-65 years were diagnosed according to DSM-IV c...

Full description

Saved in:
Bibliographic Details
Published in2014 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) pp. 1 - 4
Main Author Lebedev, Alexander V.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.09.2014
Subjects
Feature extraction
Feature Trimming
Indexes
Magnetic resonance imaging
MRI
Radio frequency
Random Forest
Schizophrenia
Support vector machine classification
Support Vector Machines
Vegetation
Online AccessGet full text
ISSN1551-2541
DOI10.1109/MLSP.2014.6958887

Cover

More Information
Summary:The goal of the MLSP 2014 Classification Challenge was to automatically detect subjects with schizophrenia and schizoaffective disorder based on multimodal features derived from the magnetic resonance imaging (MRI) data. The patients with age range of 18-65 years were diagnosed according to DSM-IV criteria. The training data consisted of 46 patients and 40 healthy controls. The test set included 119 748 subjects with unknown labels. In the present solution, we implemented so-called "feature trimming", consisting of: 1) introducing a random vector into the feature set, 2) calculating feature importance based on mean decrease of the Gini-index derived by running Random Forest classification, and 3) removing the features with importance below the "dummy variable". Support Vector Machine with Gaussian Kernel was used to run final classification with reduced feature set achieving test set AUC of 0.923.
ISSN:1551-2541
DOI:10.1109/MLSP.2014.6958887