Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment
BackgroundVascular cognitive impairment (VCI) is a major cause of cognitive impairment in the elderly and a co-factor in the development and progression of most neurodegenerative diseases. With the continuing development of neuroimaging, multiple markers can be combined to provide richer biological...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-04-01
|
| Series: | Frontiers in Aging Neuroscience |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnagi.2024.1364808/full |
| _version_ | 1827292642559393792 |
|---|---|
| author | Zihao Li Zihao Li Meini Wu Meini Wu Changhao Yin Zhenqi Wang Jianhang Wang Jianhang Wang Lingyu Chen Lingyu Chen Weina Zhao Weina Zhao |
| author_facet | Zihao Li Zihao Li Meini Wu Meini Wu Changhao Yin Zhenqi Wang Jianhang Wang Jianhang Wang Lingyu Chen Lingyu Chen Weina Zhao Weina Zhao |
| author_sort | Zihao Li |
| collection | DOAJ |
| description | BackgroundVascular cognitive impairment (VCI) is a major cause of cognitive impairment in the elderly and a co-factor in the development and progression of most neurodegenerative diseases. With the continuing development of neuroimaging, multiple markers can be combined to provide richer biological information, but little is known about their diagnostic value in VCI.MethodsA total of 83 subjects participated in our study, including 32 patients with vascular cognitive impairment with no dementia (VCIND), 21 patients with vascular dementia (VD), and 30 normal controls (NC). We utilized resting-state quantitative electroencephalography (qEEG) power spectra, structural magnetic resonance imaging (sMRI) for feature screening, and combined them with support vector machines to predict VCI patients at different disease stages.ResultsThe classification performance of sMRI outperformed qEEG when distinguishing VD from NC (AUC of 0.90 vs. 0,82), and sMRI also outperformed qEEG when distinguishing VD from VCIND (AUC of 0.8 vs. 0,0.64), but both underperformed when distinguishing VCIND from NC (AUC of 0.58 vs. 0.56). In contrast, the joint model based on qEEG and sMRI features showed relatively good classification accuracy (AUC of 0.72) to discriminate VCIND from NC, higher than that of either qEEG or sMRI alone.ConclusionPatients at varying stages of VCI exhibit diverse levels of brain structure and neurophysiological abnormalities. EEG serves as an affordable and convenient diagnostic means to differentiate between different VCI stages. A machine learning model that utilizes EEG and sMRI as composite markers is highly valuable in distinguishing diverse VCI stages and in individually tailoring the diagnosis. |
| first_indexed | 2024-04-24T13:09:21Z |
| format | Article |
| id | doaj.art-30c5e53780f84b6abf750090d0720e6a |
| institution | Directory Open Access Journal |
| issn | 1663-4365 |
| language | English |
| last_indexed | 2024-04-24T13:09:21Z |
| publishDate | 2024-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Aging Neuroscience |
| spelling | doaj.art-30c5e53780f84b6abf750090d0720e6a2024-04-05T04:55:17ZengFrontiers Media S.A.Frontiers in Aging Neuroscience1663-43652024-04-011610.3389/fnagi.2024.13648081364808Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairmentZihao Li0Zihao Li1Meini Wu2Meini Wu3Changhao Yin4Zhenqi Wang5Jianhang Wang6Jianhang Wang7Lingyu Chen8Lingyu Chen9Weina Zhao10Weina Zhao11Department of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaDepartment of Neurology, Taizhou Second People’s Hospital, Taizhou, Zhejiang, ChinaDepartment of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaDepartment of Neurology, Taizhou Second People’s Hospital, Taizhou, Zhejiang, ChinaDepartment of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaDepartment of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaDepartment of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaMudanjiang Medical College, Mudanjiang, ChinaDepartment of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaMudanjiang Medical College, Mudanjiang, ChinaDepartment of Neurology, Hongqi Hospital Affiliated to Mudanjiang Medical University, Mudanjiang, ChinaCenter for Mudanjiang North Medicine Resource Development and Application Collaborative Innovation, Mudanjiang, ChinaBackgroundVascular cognitive impairment (VCI) is a major cause of cognitive impairment in the elderly and a co-factor in the development and progression of most neurodegenerative diseases. With the continuing development of neuroimaging, multiple markers can be combined to provide richer biological information, but little is known about their diagnostic value in VCI.MethodsA total of 83 subjects participated in our study, including 32 patients with vascular cognitive impairment with no dementia (VCIND), 21 patients with vascular dementia (VD), and 30 normal controls (NC). We utilized resting-state quantitative electroencephalography (qEEG) power spectra, structural magnetic resonance imaging (sMRI) for feature screening, and combined them with support vector machines to predict VCI patients at different disease stages.ResultsThe classification performance of sMRI outperformed qEEG when distinguishing VD from NC (AUC of 0.90 vs. 0,82), and sMRI also outperformed qEEG when distinguishing VD from VCIND (AUC of 0.8 vs. 0,0.64), but both underperformed when distinguishing VCIND from NC (AUC of 0.58 vs. 0.56). In contrast, the joint model based on qEEG and sMRI features showed relatively good classification accuracy (AUC of 0.72) to discriminate VCIND from NC, higher than that of either qEEG or sMRI alone.ConclusionPatients at varying stages of VCI exhibit diverse levels of brain structure and neurophysiological abnormalities. EEG serves as an affordable and convenient diagnostic means to differentiate between different VCI stages. A machine learning model that utilizes EEG and sMRI as composite markers is highly valuable in distinguishing diverse VCI stages and in individually tailoring the diagnosis.https://www.frontiersin.org/articles/10.3389/fnagi.2024.1364808/fullmachine learningquantitative electroencephalogramvascular cognitive dysfunctionstructural magnetic resonance imagingapplications of support vector machine |
| spellingShingle | Zihao Li Zihao Li Meini Wu Meini Wu Changhao Yin Zhenqi Wang Jianhang Wang Jianhang Wang Lingyu Chen Lingyu Chen Weina Zhao Weina Zhao Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment Frontiers in Aging Neuroscience machine learning quantitative electroencephalogram vascular cognitive dysfunction structural magnetic resonance imaging applications of support vector machine |
| title | Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment |
| title_full | Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment |
| title_fullStr | Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment |
| title_full_unstemmed | Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment |
| title_short | Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment |
| title_sort | machine learning based on the eeg and structural mri can predict different stages of vascular cognitive impairment |
| topic | machine learning quantitative electroencephalogram vascular cognitive dysfunction structural magnetic resonance imaging applications of support vector machine |
| url | https://www.frontiersin.org/articles/10.3389/fnagi.2024.1364808/full |
| work_keys_str_mv | AT zihaoli machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT zihaoli machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT meiniwu machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT meiniwu machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT changhaoyin machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT zhenqiwang machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT jianhangwang machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT jianhangwang machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT lingyuchen machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT lingyuchen machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT weinazhao machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment AT weinazhao machinelearningbasedontheeegandstructuralmricanpredictdifferentstagesofvascularcognitiveimpairment |