Accuracy of automated classification of major depressive disorder as a function of symptom severity
Background: Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD). As symptom severity may influence brain activity, we investigated whether the severity of MDD affected the accuracies of machine learned MDD-vs-...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2016-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158216301322 |
| _version_ | 1818364482654568448 |
|---|---|
| author | Rajamannar Ramasubbu, MD, FRCPC, MSc Matthew R.G. Brown, PhD Filmeno Cortese, MSc Ismael Gaxiola, MSc Bradley Goodyear, PhD Andrew J. Greenshaw, PhD Serdar M. Dursun, MD, PhD Russell Greiner, PhD |
| author_facet | Rajamannar Ramasubbu, MD, FRCPC, MSc Matthew R.G. Brown, PhD Filmeno Cortese, MSc Ismael Gaxiola, MSc Bradley Goodyear, PhD Andrew J. Greenshaw, PhD Serdar M. Dursun, MD, PhD Russell Greiner, PhD |
| author_sort | Rajamannar Ramasubbu, MD, FRCPC, MSc |
| collection | DOAJ |
| description | Background: Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD). As symptom severity may influence brain activity, we investigated whether the severity of MDD affected the accuracies of machine learned MDD-vs-Control diagnostic classifiers.
Methods: Forty-five medication-free patients with DSM-IV defined MDD and 19 healthy controls participated in the study. Based on depression severity as determined by the Hamilton Rating Scale for Depression (HRSD), MDD patients were sorted into three groups: mild to moderate depression (HRSD 14–19), severe depression (HRSD 20–23), and very severe depression (HRSD ≥24). We collected functional magnetic resonance imaging (fMRI) data during both resting-state and an emotional-face matching task. Patients in each of the three severity groups were compared against controls in separate analyses, using either the resting-state or task-based fMRI data. We use each of these six datasets with linear support vector machine (SVM) binary classifiers for identifying individuals as patients or controls.
Results: The resting-state fMRI data showed statistically significant classification accuracy only for the very severe depression group (accuracy 66%, p = 0.012 corrected), while mild to moderate (accuracy 58%, p = 1.0 corrected) and severe depression (accuracy 52%, p = 1.0 corrected) were only at chance. With task-based fMRI data, the automated classifier performed at chance in all three severity groups.
Conclusions: Binary linear SVM classifiers achieved significant classification of very severe depression with resting-state fMRI, but the contribution of brain measurements may have limited potential in differentiating patients with less severe depression from healthy controls. |
| first_indexed | 2024-12-13T22:05:04Z |
| format | Article |
| id | doaj.art-2c5dfd20983140f6ad4c1a6b663a9b11 |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-12-13T22:05:04Z |
| publishDate | 2016-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-2c5dfd20983140f6ad4c1a6b663a9b112022-12-21T23:29:52ZengElsevierNeuroImage: Clinical2213-15822016-01-0112C32033110.1016/j.nicl.2016.07.012Accuracy of automated classification of major depressive disorder as a function of symptom severityRajamannar Ramasubbu, MD, FRCPC, MSc0Matthew R.G. Brown, PhD1Filmeno Cortese, MSc2Ismael Gaxiola, MSc3Bradley Goodyear, PhD4Andrew J. Greenshaw, PhD5Serdar M. Dursun, MD, PhD6Russell Greiner, PhD7Department of Psychiatry, University of Calgary, Calgary, AB, CanadaDepartment of Psychiatry, University of Alberta, Edmonton, AB, CanadaHotchkiss Brain Institute, University of Calgary, Calgary, AB, CanadaHotchkiss Brain Institute, University of Calgary, Calgary, AB, CanadaHotchkiss Brain Institute, University of Calgary, Calgary, AB, CanadaDepartment of Psychiatry, University of Alberta, Edmonton, AB, CanadaDepartment of Psychiatry, University of Alberta, Edmonton, AB, CanadaDepartment of Computing Science, University of Alberta, Edmonton, AB, CanadaBackground: Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD). As symptom severity may influence brain activity, we investigated whether the severity of MDD affected the accuracies of machine learned MDD-vs-Control diagnostic classifiers. Methods: Forty-five medication-free patients with DSM-IV defined MDD and 19 healthy controls participated in the study. Based on depression severity as determined by the Hamilton Rating Scale for Depression (HRSD), MDD patients were sorted into three groups: mild to moderate depression (HRSD 14–19), severe depression (HRSD 20–23), and very severe depression (HRSD ≥24). We collected functional magnetic resonance imaging (fMRI) data during both resting-state and an emotional-face matching task. Patients in each of the three severity groups were compared against controls in separate analyses, using either the resting-state or task-based fMRI data. We use each of these six datasets with linear support vector machine (SVM) binary classifiers for identifying individuals as patients or controls. Results: The resting-state fMRI data showed statistically significant classification accuracy only for the very severe depression group (accuracy 66%, p = 0.012 corrected), while mild to moderate (accuracy 58%, p = 1.0 corrected) and severe depression (accuracy 52%, p = 1.0 corrected) were only at chance. With task-based fMRI data, the automated classifier performed at chance in all three severity groups. Conclusions: Binary linear SVM classifiers achieved significant classification of very severe depression with resting-state fMRI, but the contribution of brain measurements may have limited potential in differentiating patients with less severe depression from healthy controls.http://www.sciencedirect.com/science/article/pii/S2213158216301322Major depressionSeverity of symptomsDiagnosisFunctional magnetic resonance imagingMachine learningClassificationSupport vector machine |
| spellingShingle | Rajamannar Ramasubbu, MD, FRCPC, MSc Matthew R.G. Brown, PhD Filmeno Cortese, MSc Ismael Gaxiola, MSc Bradley Goodyear, PhD Andrew J. Greenshaw, PhD Serdar M. Dursun, MD, PhD Russell Greiner, PhD Accuracy of automated classification of major depressive disorder as a function of symptom severity NeuroImage: Clinical Major depression Severity of symptoms Diagnosis Functional magnetic resonance imaging Machine learning Classification Support vector machine |
| title | Accuracy of automated classification of major depressive disorder as a function of symptom severity |
| title_full | Accuracy of automated classification of major depressive disorder as a function of symptom severity |
| title_fullStr | Accuracy of automated classification of major depressive disorder as a function of symptom severity |
| title_full_unstemmed | Accuracy of automated classification of major depressive disorder as a function of symptom severity |
| title_short | Accuracy of automated classification of major depressive disorder as a function of symptom severity |
| title_sort | accuracy of automated classification of major depressive disorder as a function of symptom severity |
| topic | Major depression Severity of symptoms Diagnosis Functional magnetic resonance imaging Machine learning Classification Support vector machine |
| url | http://www.sciencedirect.com/science/article/pii/S2213158216301322 |
| work_keys_str_mv | AT rajamannarramasubbumdfrcpcmsc accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT matthewrgbrownphd accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT filmenocortesemsc accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT ismaelgaxiolamsc accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT bradleygoodyearphd accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT andrewjgreenshawphd accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT serdarmdursunmdphd accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity AT russellgreinerphd accuracyofautomatedclassificationofmajordepressivedisorderasafunctionofsymptomseverity |