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.
Similar content being viewed by others
Change history
23 July 2021
A Correction to this paper has been published: https://doi.org/10.1007/s00330-021-07757-5
Abbreviations
- MIV:
-
Mean impact value
- MR:
-
Magnetic resonance
- PD:
-
Parkinson’s disease
- PD-MCI:
-
Parkinson’s disease with mild cognitive impairment
- PD-NC:
-
Parkinson’s disease with normal cognition
- QEEG:
-
Quantitative electroencephalogram
- ROC:
-
Receiver operating characteristic
- SBM:
-
Surface-based morphometry
- SVM:
-
Support vector machine
References
Duncan GW, Khoo TK, Yarnall AJ et al (2014) Health-related quality of life in early Parkinson’s disease: the impact of nonmotor symptoms. Mov Disord 29(2):195–202
Savica R, Grossardt BR, Rocca WA, Bower JH (2018) Parkinson disease with and without dementia: a prevalence study and future projections. Mov Disord 33(4):537–543
Winer JR, Maass A, Pressman P et al (2018) Associations between tau, beta-amyloid, and cognition in Parkinson disease. JAMA Neurol 75(2):227–235
Aarsland D, Creese B, Politis M et al (2017) Cognitive decline in Parkinson disease. Nat Rev Neurol 13(4):217–231
Backstrom D, Granasen G, Domellof ME et al (2018) Early predictors of mortality in parkinsonism and Parkinson disease: a population-based study. Neurology 91(22):e2045–e2056
Litvan I, Kieburtz K, Troster AI, Aarsland D (2018) Strengths and challenges in conducting clinical trials in Parkinson’s disease mild cognitive impairment. Mov Disord 33(4):520–527
Meyer PT, Frings L, Rücker G, Hellwig S (2017) (18)F-FDG PET in parkinsonism: differential diagnosis and cognitive impairment in Parkinson’s disease. J Nucl Med 58(12)
Glaab E, Trezzi JP, Greuel A et al (2019) Integrative analysis of blood metabolomics and PET brain neuroimaging data for Parkinson’s disease. Neurobiol Dis 124:555–562
Kalia LV (2018) Biomarkers for cognitive dysfunction in Parkinson’s disease. Parkinsonism Relat Disord 46(Suppl 1):S19–S23
Lanskey JH, Mccolgan P, Schrag AE et al (2018) Can neuroimaging predict dementia in Parkinson’s disease? Brain 141(9):2545–2560
Svenningsson P, Westman E, Ballard C, Aarsland D (2012) Cognitive impairment in patients with Parkinson’s disease: diagnosis, biomarkers, and treatment. Lancet Neurol 11(8):697–707
Delgado-Alvarado M, Gago B, Navalpotro-Gomez I, Jimenez-Urbieta H, Rodriguez-Oroz MC (2016) Biomarkers for dementia and mild cognitive impairment in Parkinson’s disease. Mov Disord 31(6):861–881
Arnaldi D, De Carli F, Fama F et al (2017) Prediction of cognitive worsening in de novo Parkinson’s disease: clinical use of biomarkers. Mov Disord 32(12):1738–1747
Betrouni N, Delval A, Chaton L et al (2019) Electroencephalography-based machine learning for cognitive profiling in Parkinson’s disease: preliminary results. Mov Disord 34(2):210–217
Morales DA, Vives-Gilabert Y, Gomez-Anson B et al (2013) Predicting dementia development in Parkinson’s disease using Bayesian network classifiers. Psychiatry Res 213(2):92–98
Gelb DJ, Oliver E, Gilman S (1999) Diagnostic criteria for Parkinson disease. Arch Neurol 56(1):33–39
Emre M, Aarsland D, Brown R et al (2007) Clinical diagnostic criteria for dementia associated with Parkinson’s disease. Mov Disord 22(12):1689–1707 quiz 1837
Litvan I, Goldman JG, Troster AI et al (2012) Diagnostic criteria for mild cognitive impairment in Parkinson's disease: Movement Disorder Society Task Force guidelines. Mov Disord 27(3):349–356
Mckeown M (2003) Independent component analysis of functional MRI: what is signal and what is noise? Curr Opin Neurobiol 13(5):620–629
Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):1–27
Gromski PS, Xu Y, Correa E et al (2014) A comparative investigation of modern feature selection and classification approaches for the analysis of mass spectrometry data. Anal Chim Acta 829:1–8
Jiang JL, Su X, Zhang H, Zhang XH, Yuan YJ (2013) A novel approach to active compounds identification based on support vector regression model and mean impact value. Chem Biol Drug Des 81(5):650–657
Zhang JH, Han X, Zhao HW et al (2018) Personalized prediction model for seizure-free epilepsy with levetiracetam therapy: a retrospective d ata analysis using support vector machine. Br J Clin Pharmacol 84(11):2615–2624
Gao Y, Nie K, Mei M et al (2018) Changes in cortical thickness in patients with early Parkinson’s disease at different Hoehn and Yahr stages. Front Hum Neurosci 12:469
Kamagata K, Motoi Y, Tomiyama H et al (2013) Relationship between cognitive impairment and white-matter alteration in Parkinson's disease with dem entia: tract-based spatial statistics and tract-specific analysis. Eur Radiol 23(7):1946–1955
Caviness JN, Lue LF, Hentz JG et al (2016) Cortical phosphorylated alpha-Synuclein levels correlate with brain wave spectra in Parkinson’s disease. Mov Disord 31(7):1012–1019
De Benedictis A, Duffau H (2011) Brain hodotopy: from esoteric concept to practical surgical applications. Neurosurgery 68(6):1709–1723 discussion 1723
Wolters AF, van de Weijer SCF, Leentjens AFG, Duits AA, Jacobs HIL, Kuijf ML (2019) Resting-state fMRI in Parkinson's disease patients with cognitive impairment: a meta-analysis. Parkinsonism Relat Disord 62:16–27
Wang W, Mei M, Gao Y et al (2020) Changes of brain structural network connection in Parkinson’s disease patients with mild cognitive dy sfunction: a study based on diffusion tensor imaging. J Neurol 267(4):933–943
Bratic B, Kurbalija V, Ivanovic M, Oder I, Bosnic Z (2018) Machine learning for predicting cognitive diseases: methods, data sources and risk factors. J Med Syst 42(12):243
Ma Z, Wang P, Gao Z, Wang R, Khalighi K (2018) Ensemble of machine learning algorithms using the stacked generalization approach to estimate the warfarin dose. PLoS One 13(10):e0205872
Bonanni L (2019) The democratic aspect of machine learning: limitations and opportunities for Parkinson’s disease. Mov Disord 34(2):164–166
Schrag A, Siddiqui UF, Anastasiou Z, Weintraub D, Schott JM (2017) Clinical variables and biomarkers in prediction of cognitive impairment in patients with newly diagnosed Parkinson’s disease: a cohort study. Lancet Neurol 16(1):66–75
Liu G, Locascio JJ, Corvol JC et al (2017) Prediction of cognition in Parkinson’s disease with a clinical-genetic score: a longitudinal analysis of nine cohorts. Lancet Neurol 16(8):620–629
Anang JB, Gagnon JF, Bertrand JA et al (2014) Predictors of dementia in Parkinson disease: a prospective cohort study. Neurology 83(14):1253–1260
Prashanth R, Dutta RS, Mandal PK, Ghosh S (2016) High-accuracy detection of early Parkinson’s disease through multimodal features and machine learning. Int J Med Inform 90:13–21
Acknowledgements
We thank the support of the patients, their families, and control subjects for the study.
Funding
This study has received funding from the National Natural Science Foundation of China (No. 81501112), Guangdong Natural Science Foundation (No. 2016A030310327), Guangdong Natural Science Foundation (No. 2019A1515110061), National Key R&D Program of China (No. 2017YFC1310200), The Fundamental Research Funds for the Central Universities (No. 2018MS27), Key Program of Natural Science Foundation of Guangdong Province, China (No. 2017B030311015), Guangzhou Municipal People’s Livelihood Science and Technology Project (No. 201803010085), and Medical Science and Technology Foundation of Guangdong Province (No. A2018137).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Guarantor
The guarantor name of this publication is Lijuan Wang.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
One of the authors has significant statistical expertise.
Informed consent
Written informed consent was obtained from all subjects (patients) in this study.
Ethical approval
The study had been approved by Guangdong General Hospital for Research with Human Subjects (Ethical Approval No. GDREC2015195H).
Study subjects or cohorts overlap
Some study subjects or cohorts have been previously reported in the article (Gao, Y., K. Nie, M. Mei, et al, Changes in Cortical Thickness in Patients With Early Parkinson’s Disease at Different Hoehn and Yahr Stages. Front Hum Neurosci, 2018. 12: p. 469.)
Methodology
• retrospective
• observational
• performed at one institution
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
The original online version of this article was revised: The information was missing that Jiahui Zhang and Yuyuan Gao are co-first authors and that Kun Nie and Lijuan Wang are co-corresponding authors, and the presentation of Figure 2 was incorrect.
Jiahui Zhang and Yuyuan Gao are co-first authors.
Kun Nie and Lijuan Wang are co-corresponding authors
Rights and permissions
About this article
Cite this article
Zhang, J., Gao, Y., He, X. et al. Identifying Parkinson’s disease with mild cognitive impairment by using combined MR imaging and electroencephalogram. Eur Radiol 31, 7386–7394 (2021). https://doi.org/10.1007/s00330-020-07575-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00330-020-07575-1