Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine
Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one i...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Online |
| Language: | English |
| Published: |
Academic Press
2011
|
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3191277/ |
| id |
pubmed-3191277 |
|---|---|
| recordtype |
oai_dc |
| spelling |
pubmed-31912772011-12-15 Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine Mourão-Miranda, Janaina Hardoon, David R. Hahn, Tim Marquand, Andre F. Williams, Steve C.R. Shawe-Taylor, John Brammer, Michael Article Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers. Academic Press 2011-10-01 /pmc/articles/PMC3191277/ /pubmed/21723950 http://dx.doi.org/10.1016/j.neuroimage.2011.06.042 Text en © 2011 Elsevier Inc. https://creativecommons.org/licenses/by/3.0/ Open Access under CC BY 3.0 (https://creativecommons.org/licenses/by/3.0/) license |
| repository_type |
Open Access Journal |
| institution_category |
Foreign Institution |
| institution |
US National Center for Biotechnology Information |
| building |
NCBI PubMed |
| collection |
Online Access |
| language |
English |
| format |
Online |
| author |
Mourão-Miranda, Janaina Hardoon, David R. Hahn, Tim Marquand, Andre F. Williams, Steve C.R. Shawe-Taylor, John Brammer, Michael |
| spellingShingle |
Mourão-Miranda, Janaina Hardoon, David R. Hahn, Tim Marquand, Andre F. Williams, Steve C.R. Shawe-Taylor, John Brammer, Michael Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine |
| author_facet |
Mourão-Miranda, Janaina Hardoon, David R. Hahn, Tim Marquand, Andre F. Williams, Steve C.R. Shawe-Taylor, John Brammer, Michael |
| author_sort |
Mourão-Miranda, Janaina |
| title |
Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine |
| title_short |
Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine |
| title_full |
Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine |
| title_fullStr |
Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine |
| title_full_unstemmed |
Patient classification as an outlier detection problem: An application of the One-Class Support Vector Machine |
| title_sort |
patient classification as an outlier detection problem: an application of the one-class support vector machine |
| description |
Pattern recognition approaches, such as the Support Vector Machine (SVM), have been successfully used to classify groups of individuals based on their patterns of brain activity or structure. However these approaches focus on finding group differences and are not applicable to situations where one is interested in accessing deviations from a specific class or population. In the present work we propose an application of the one-class SVM (OC-SVM) to investigate if patterns of fMRI response to sad facial expressions in depressed patients would be classified as outliers in relation to patterns of healthy control subjects. We defined features based on whole brain voxels and anatomical regions. In both cases we found a significant correlation between the OC-SVM predictions and the patients' Hamilton Rating Scale for Depression (HRSD), i.e. the more depressed the patients were the more of an outlier they were. In addition the OC-SVM split the patient groups into two subgroups whose membership was associated with future response to treatment. When applied to region-based features the OC-SVM classified 52% of patients as outliers. However among the patients classified as outliers 70% did not respond to treatment and among those classified as non-outliers 89% responded to treatment. In addition 89% of the healthy controls were classified as non-outliers. |
| publisher |
Academic Press |
| publishDate |
2011 |
| url |
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3191277/ |
| _version_ |
1611480115035766784 |