Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques
Accurate classification or prediction of the brain state across individual subject, i.e., healthy, or with brain disorders, is generally a more difficult task than merely finding group differences. The former must be approached with highly informative and sensitive biomarkers as well as effective pa...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2012-08-01
|
| Series: | Frontiers in Systems Neuroscience |
| Subjects: | |
| Online Access: | http://journal.frontiersin.org/Journal/10.3389/fnsys.2012.00058/full |
| _version_ | 1819175378858541056 |
|---|---|
| author | Wei eCheng Wei eCheng Xiaoxi eJi Jie eZhang Jianfeng eFeng Jianfeng eFeng |
| author_facet | Wei eCheng Wei eCheng Xiaoxi eJi Jie eZhang Jianfeng eFeng Jianfeng eFeng |
| author_sort | Wei eCheng |
| collection | DOAJ |
| description | Accurate classification or prediction of the brain state across individual subject, i.e., healthy, or with brain disorders, is generally a more difficult task than merely finding group differences. The former must be approached with highly informative and sensitive biomarkers as well as effective pattern classification/feature selection approaches. In this paper, we propose a systematic methodology to discriminate ADHD patients from healthy controls on the individual level. Multiple neuroimaging markers that are proved to be sensitive features are identified, which include multiscale characteristics extracted from Blood Oxygenation Level Dependent (BOLD) signals, such as regional homogeneity and amplitude of low-frequency fluctuations. Functional connectivity derived from Pearson correlation, partial correlation, and spatial correlation is also utilized to reflect the abnormal patterns of functional integration, or, dysconnectivity syndromes in the brain. These neuroimaging markers are calculated on either voxel or regional level. Advanced feature selection approach is then designed, including a brain-wise association study (BWAS). Using identified features and proper feature integration, a Support Vector Machine classifier can achieve a cross-validated classification accuracy of 76.15% across individuals from a large dataset consisting of 141 healthy controls and 98 ADHD patients, with the sensitivity being 63.27% and the specificity being 85.11%. Our results show that the most discriminative features for classification are primarily associated with the frontal and cerebellar regions. The proposed methodology is expected to improve clinical diagnosis and evaluation of treatment for ADHD patient, and to have wider applications in diagnosis of general neuropsychiatric disorders. |
| first_indexed | 2024-12-22T20:53:55Z |
| format | Article |
| id | doaj.art-7825f9134ad149b98993d7b0c0bb898d |
| institution | Directory Open Access Journal |
| issn | 1662-5137 |
| language | English |
| last_indexed | 2024-12-22T20:53:55Z |
| publishDate | 2012-08-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Systems Neuroscience |
| spelling | doaj.art-7825f9134ad149b98993d7b0c0bb898d2022-12-21T18:13:00ZengFrontiers Media S.A.Frontiers in Systems Neuroscience1662-51372012-08-01610.3389/fnsys.2012.0005826720Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniquesWei eCheng0Wei eCheng1Xiaoxi eJi2Jie eZhang3Jianfeng eFeng4Jianfeng eFeng5Fudan University, Shanghai ChinaZhejiang Normal UniversityFudan University, Shanghai ChinaFudan University, Shanghai ChinaFudan University, Shanghai ChinaWarwick UniversityAccurate classification or prediction of the brain state across individual subject, i.e., healthy, or with brain disorders, is generally a more difficult task than merely finding group differences. The former must be approached with highly informative and sensitive biomarkers as well as effective pattern classification/feature selection approaches. In this paper, we propose a systematic methodology to discriminate ADHD patients from healthy controls on the individual level. Multiple neuroimaging markers that are proved to be sensitive features are identified, which include multiscale characteristics extracted from Blood Oxygenation Level Dependent (BOLD) signals, such as regional homogeneity and amplitude of low-frequency fluctuations. Functional connectivity derived from Pearson correlation, partial correlation, and spatial correlation is also utilized to reflect the abnormal patterns of functional integration, or, dysconnectivity syndromes in the brain. These neuroimaging markers are calculated on either voxel or regional level. Advanced feature selection approach is then designed, including a brain-wise association study (BWAS). Using identified features and proper feature integration, a Support Vector Machine classifier can achieve a cross-validated classification accuracy of 76.15% across individuals from a large dataset consisting of 141 healthy controls and 98 ADHD patients, with the sensitivity being 63.27% and the specificity being 85.11%. Our results show that the most discriminative features for classification are primarily associated with the frontal and cerebellar regions. The proposed methodology is expected to improve clinical diagnosis and evaluation of treatment for ADHD patient, and to have wider applications in diagnosis of general neuropsychiatric disorders.http://journal.frontiersin.org/Journal/10.3389/fnsys.2012.00058/fullADHDfunctional brain networkspattern classificfALFFReHoBWAS |
| spellingShingle | Wei eCheng Wei eCheng Xiaoxi eJi Jie eZhang Jianfeng eFeng Jianfeng eFeng Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques Frontiers in Systems Neuroscience ADHD functional brain networks pattern classific fALFF ReHo BWAS |
| title | Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques |
| title_full | Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques |
| title_fullStr | Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques |
| title_full_unstemmed | Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques |
| title_short | Individual classification of ADHD patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques |
| title_sort | individual classification of adhd patients by integrating multiscale neuroimaging markers and advanced pattern recognition techniques |
| topic | ADHD functional brain networks pattern classific fALFF ReHo BWAS |
| url | http://journal.frontiersin.org/Journal/10.3389/fnsys.2012.00058/full |
| work_keys_str_mv | AT weiecheng individualclassificationofadhdpatientsbyintegratingmultiscaleneuroimagingmarkersandadvancedpatternrecognitiontechniques AT weiecheng individualclassificationofadhdpatientsbyintegratingmultiscaleneuroimagingmarkersandadvancedpatternrecognitiontechniques AT xiaoxieji individualclassificationofadhdpatientsbyintegratingmultiscaleneuroimagingmarkersandadvancedpatternrecognitiontechniques AT jieezhang individualclassificationofadhdpatientsbyintegratingmultiscaleneuroimagingmarkersandadvancedpatternrecognitiontechniques AT jianfengefeng individualclassificationofadhdpatientsbyintegratingmultiscaleneuroimagingmarkersandadvancedpatternrecognitiontechniques AT jianfengefeng individualclassificationofadhdpatientsbyintegratingmultiscaleneuroimagingmarkersandadvancedpatternrecognitiontechniques |