Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques
Abstract Background Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifier...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2020-10-01
|
| Series: | BMC Psychiatry |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12888-020-02886-5 |
| _version_ | 1817982768035921920 |
|---|---|
| author | Hao Li Liqian Cui Liping Cao Yizhi Zhang Yueheng Liu Wenhao Deng Wenjin Zhou |
| author_facet | Hao Li Liqian Cui Liping Cao Yizhi Zhang Yueheng Liu Wenhao Deng Wenjin Zhou |
| author_sort | Hao Li |
| collection | DOAJ |
| description | Abstract Background Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD. Methods In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed. Results After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5–95.3%), sensitivity of 86.4% (95%CI: 64.0–96.4%), and specificity of 88.9% (95%CI: 63.9–98.0%) in the test data (p = 0.0022). Conclusions A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic. |
| first_indexed | 2024-04-13T23:24:41Z |
| format | Article |
| id | doaj.art-dc14f3de377642729f4bb21cb892993a |
| institution | Directory Open Access Journal |
| issn | 1471-244X |
| language | English |
| last_indexed | 2024-04-13T23:24:41Z |
| publishDate | 2020-10-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Psychiatry |
| spelling | doaj.art-dc14f3de377642729f4bb21cb892993a2022-12-22T02:25:07ZengBMCBMC Psychiatry1471-244X2020-10-0120111210.1186/s12888-020-02886-5Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniquesHao Li0Liqian Cui1Liping Cao2Yizhi Zhang3Yueheng Liu4Wenhao Deng5Wenjin Zhou6Department of Neurology, The First Affiliated Hospital, Sun Yat-sen UniversityDepartment of Neurology, The First Affiliated Hospital, Sun Yat-sen UniversityAffiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai HospitalAffiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai HospitalDepartment of Psychiatry, The Second Xiangya Hospital, Central South UniversityAffiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai HospitalAffiliated Brain Hospital of Guangzhou Medical University, Guangzhou Huiai HospitalAbstract Background Bipolar disorder (BPD) is a common mood disorder that is often goes misdiagnosed or undiagnosed. Recently, machine learning techniques have been combined with neuroimaging methods to aid in the diagnosis of BPD. However, most studies have focused on the construction of classifiers based on single-modality MRI. Hence, in this study, we aimed to construct a support vector machine (SVM) model using a combination of structural and functional MRI, which could be used to accurately identify patients with BPD. Methods In total, 44 patients with BPD and 36 healthy controls were enrolled in the study. Clinical evaluation and MRI scans were performed for each subject. Next, image pre-processing, VBM and ReHo analyses were performed. The ReHo values of each subject in the clusters showing significant differences were extracted. Further, LASSO approach was recruited to screen features. Based on selected features, the SVM model was established, and discriminant analysis was performed. Results After using the two-sample t-test with multiple comparisons, a total of 8 clusters were extracted from the data (VBM = 6; ReHo = 2). Next, we used both VBM and ReHo data to construct the new SVM classifier, which could effectively identify patients with BPD at an accuracy of 87.5% (95%CI: 72.5–95.3%), sensitivity of 86.4% (95%CI: 64.0–96.4%), and specificity of 88.9% (95%CI: 63.9–98.0%) in the test data (p = 0.0022). Conclusions A combination of structural and functional MRI can be of added value in the construction of SVM classifiers to aid in the accurate identification of BPD in the clinic.http://link.springer.com/article/10.1186/s12888-020-02886-5Bipolar disorderMultimodality magnetic resonance imagingSupport vector machine |
| spellingShingle | Hao Li Liqian Cui Liping Cao Yizhi Zhang Yueheng Liu Wenhao Deng Wenjin Zhou Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques BMC Psychiatry Bipolar disorder Multimodality magnetic resonance imaging Support vector machine |
| title | Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques |
| title_full | Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques |
| title_fullStr | Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques |
| title_full_unstemmed | Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques |
| title_short | Identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques |
| title_sort | identification of bipolar disorder using a combination of multimodality magnetic resonance imaging and machine learning techniques |
| topic | Bipolar disorder Multimodality magnetic resonance imaging Support vector machine |
| url | http://link.springer.com/article/10.1186/s12888-020-02886-5 |
| work_keys_str_mv | AT haoli identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques AT liqiancui identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques AT lipingcao identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques AT yizhizhang identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques AT yuehengliu identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques AT wenhaodeng identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques AT wenjinzhou identificationofbipolardisorderusingacombinationofmultimodalitymagneticresonanceimagingandmachinelearningtechniques |