Jiahui Zhang1,2, Yuyuan Gao2, Xuetao He3, Shujun Feng2, Jinlong Hu4, Qingxi Zhang2, Jiehao Zhao2, Zhiheng Huang2, Limin Wang2, Guixian Ma2, Yuhu Zhang2, Kun Nie5, Lijuan Wang6,7. 1. The Second School of Clinical Medicine, Southern Medical University, No.1023, South Shatai Road, Baiyun District, Guangzhou, 510515, China. 2. Department of Neurology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangdong Neuroscience Institute, No.106, Zhongshan 2nd Road, Yuexiu District, Guangzhou, 510080, China. 3. Department of Neuroelectrophysiology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, 510080, China. 4. Communication and Computer Network Lab of Guangdong, School of Computer Science and Engineering, South China University of Technology, Guangzhou, 510641, China. 5. Department of Neurology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangdong Neuroscience Institute, No.106, Zhongshan 2nd Road, Yuexiu District, Guangzhou, 510080, China. nk20080911@126.com. 6. The Second School of Clinical Medicine, Southern Medical University, No.1023, South Shatai Road, Baiyun District, Guangzhou, 510515, China. wljgd68@163.com. 7. Department of Neurology, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangdong Neuroscience Institute, No.106, Zhongshan 2nd Road, Yuexiu District, Guangzhou, 510080, China. wljgd68@163.com.
Abstract
OBJECTIVES: To analyse the changes of quantitative electroencephalogram (qEEG) and cortex structural magnetic resonance (MR) imaging in Parkinson's disease with mild cognitive impairment (PD-MCI) and to explore the "composite marker"-based machine learning model in identifying PD-MCI. METHODS: Retrospective analysis of patients with PD identified 36 PD-MCI and 35 PD with normal cognition (PD-NC). QEEG features of power spectrum and structural MR features of cortex based on surface-based morphometry (SBM) were extracted. Support vector machine (SVM) was established using combined features of structural MR and qEEG to identify PD-MCI. Feature importance evaluation algorithm of mean impact value (MIV) was established to sort the vital characteristics of qEEG and structural MR. RESULTS: Compared with PD-NC, PD-MCI showed a statistically significant difference in 5 leads and waves of qEEG and 7 cortical region features of structural MR. The SVM model based on these qEEG and structural MR features yielded an accuracy of 0.80 in the training set and had a high prediction accuracy of 0.80 in the test set (sensitivity was 0.78, specificity was 0.83, area under the receiver operating characteristic curve was 0.77), which was higher than the model built by the feature separately. QEEG features of theta wave in C3 had a marked impact on the model for classification according to the MIV algorithm. CONCLUSIONS: PD-MCI is characterized by widespread structural and EEG abnormality. "Composite markers" could be valuable for the individualized diagnosis of PD-MCI by machine learning. KEY POINTS: • Explore the brain abnormalities in Parkinson's disease with mild cognitive impairment by using the quantitative electroencephalogram and cortex structural MR simultaneously. • Multimodal features based support vector machine for identifying Parkinson's disease with mild cognitive impairment has an acceptable performance. • Theta wave in C3 is the most influential feature of qEEG and cortex structure MR imaging in identifying Parkinson's disease with mild cognitive impairment using support vector machine.
OBJECTIVES: To analyse the changes of quantitative electroencephalogram (qEEG) and cortex structural magnetic resonance (MR) imaging in Parkinson's disease with mild cognitive impairment (PD-MCI) and to explore the "composite marker"-based machine learning model in identifying PD-MCI. METHODS: Retrospective analysis of patients with PD identified 36 PD-MCI and 35 PD with normal cognition (PD-NC). QEEG features of power spectrum and structural MR features of cortex based on surface-based morphometry (SBM) were extracted. Support vector machine (SVM) was established using combined features of structural MR and qEEG to identify PD-MCI. Feature importance evaluation algorithm of mean impact value (MIV) was established to sort the vital characteristics of qEEG and structural MR. RESULTS: Compared with PD-NC, PD-MCI showed a statistically significant difference in 5 leads and waves of qEEG and 7 cortical region features of structural MR. The SVM model based on these qEEG and structural MR features yielded an accuracy of 0.80 in the training set and had a high prediction accuracy of 0.80 in the test set (sensitivity was 0.78, specificity was 0.83, area under the receiver operating characteristic curve was 0.77), which was higher than the model built by the feature separately. QEEG features of theta wave in C3 had a marked impact on the model for classification according to the MIV algorithm. CONCLUSIONS: PD-MCI is characterized by widespread structural and EEG abnormality. "Composite markers" could be valuable for the individualized diagnosis of PD-MCI by machine learning. KEY POINTS: • Explore the brain abnormalities in Parkinson's disease with mild cognitive impairment by using the quantitative electroencephalogram and cortex structural MR simultaneously. • Multimodal features based support vector machine for identifying Parkinson's disease with mild cognitive impairment has an acceptable performance. • Theta wave in C3 is the most influential feature of qEEG and cortex structure MR imaging in identifying Parkinson's disease with mild cognitive impairment using support vector machine.
Authors: Juliette H Lanskey; Peter McColgan; Anette E Schrag; Julio Acosta-Cabronero; Geraint Rees; Huw R Morris; Rimona S Weil Journal: Brain Date: 2018-09-01 Impact factor: 13.501