Differentiating Early and Late Stage Parkinson's Disease Patients from Healthy Controls
DOI:
https://doi.org/10.14738/jbemi.36.2280Keywords:
Parkinson’s disease, SSM/PCA, decision tree classificationAbstract
Parkinson’s disease (PD) is a neurodegenerative disease which is difficult to diagnose at an early stage. Brain imaging techniques like [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET) may aid to identify disease-related changes in cerebral glucose metabolism. The scaled subprofile model with principal component analysis (SSM/PCA) is applied to FDG-PET data to extract features and corresponding patterns of glucose metabolism which can be used to distinguish PD subjects from healthy controls. From a previous study, the decision tree (DT) classifier’s performance to separate the PD group from healthy controls was below chance level. This could be attributed to the small number of subjects in the dataset, combined with the early disease progression. In this study, we make use of an additional PD dataset, consisting of subject brain images obtained at a later disease stage. The features extracted by the SSM/PCA method are used for distinguishing PD subjects from healthy controls using three classification methods, that is, decision trees, Generalized Matrix Learning Vector Quantization (GMLVQ), and Support Vector Machine (SVM) with linear kernel. The classifiers are validated to determine their capability of classification given new subject data. We compare the classifiers’ performances on the distinct early-stage and late-stage datasets, as well on the combined datasets. We also use the early and late-stage datasets interchangeably for training and testing the classifiers. We find that the DT classification performance on the late-stage dataset is considerably better than in the previous study, where we used early-stage data. For early-stage patients, the application of the GMLVQ and SVM classifiers gives a significant improvement as compared to the DT classifier.References
(1) Hughes, A. J., Daniel, S. E., Ben-Shlomo, Y., Lees, A. J., 2002. The accuracy of diagnosis of parkinsonian syndromes in a specialist movement disorder service. Brain 125 (4), 861–870.
(2) Osaki, Y., Ben-Shlomo, Y., Lees, A. J., Daniel, S. E., Colosimo, C., Wenning, G., Quinn, N., 2004. Accuracy of clinical diagnosis of progressive supranuclear palsy. Movement disorders 19 (2), 181–189.
(3) Moeller, J. R., Strother, S. C., Sidtis, J. J., Rottenberg, D. A., 1987. Scaled subprofile model: a statistical approach to the analysis of functional patterns in positron emission tomographic data. J Cereb Blood Flow Metab 7 (5), 649–58.
(4) Eidelberg, D., 2009. Metabolic brain networks in neurodegenerative disorders: a functional imaging approach. Trends in Neurosciences 32 (10), 548–557.
(5) Niethammer, M., Eidelberg, D., 2012. Metabolic brain networks in translational neurology: concepts and applications. Annals of neurology 72 (5), 635–647.
(6) Quinlan, J. R., 1993. C4.5: Programs for Machine Learning. Morgan Kaufmann, San Mateo, USA.
(7) Mudali, D., Teune, L. K., Renken, R. J., Leenders, K. L., Roerdink, J. B. T. M., 2015. Classification of Parkinsonian syndromes from FDG-PET brain data using decision trees with SSM/PCA features. Computational and Mathematical Methods in Medicine Article ID 136921, 1–10.
(8) Eckert, T., Tang, C., Eidelberg, D., 2007. Assessment of the progression of Parkinson’s disease: a metabolic network approach. The Lancet Neurology 6 (10), 926–932.
(9) Moeller, J. R., Strother, S. C., 1991. A regional covariance approach to the analysis of functional patterns in positron emission tomographic data. J Cereb Blood Flow Metab 11 (2), A121–135.
(10) Al Snousy, M. B., El-Deeb, H. M., Badran, K., Al Khlil, I. A., 2011. Suite of decision tree-based classification algorithms on cancer gene expression data. Egyptian Informatics Journal 12 (2), 73–82.
(11) Magnin, B., Mesrob, L., Kinkingn´ehun, S., P´el´egrini-Issac, M., Colliot, O., Sarazin, M., Dubois, B., Leh´ericy, S., Benali, H., 2009. Support vector machine-based classification of Alzheimer’s disease from whole-brain anatomical MRI. Neuroradiology 51 (2), 73–83.
(12) Haller, S., Badoud, S., Nguyen, D., Garibotto, V., Lovblad, K., Burkhard, P., 2012. Individual detection of patients with Parkinson disease using support vector machine analysis of diffusion tensor imaging data: initial results. American Journal of Neuroradiology 33 (11), 2123–2128.
(13) Orr`u, G., Pettersson-Yeo, W., Marquand, A. F., Sartori, G., Mechelli, A., 2012. Using support vector machine to identify imaging biomarkers of neurological and psychiatric disease: a critical review. Neuroscience & Biobehavioral Reviews 36 (4), 1140–1152.
(14) Yeo, L., Adlard, N., Biehl, M., Juarez, M., Smallie, T., Snow, M., Buckley, C., Raza, K., Filer, A., Scheel-Toellner, D., 2015. Expression of chemokines CXCL4 and CXCL7 by synovial macrophages defines an early stage of rheumatoid arthritis. Annals of the rheumatic diseases, annrheumdis–2014.
(15) Schneider, P., Biehl, M., Hammer, B., 2009. Adaptive relevance matrices in learning vector quantization. Neural Computation 21 (12), 3532–3561.
(16) Garc´ıa-Garc´ıa, D., Clavero, P., Salas, C. G., Lamet, I., Arbizu, J., Gonzalez-Redondo, R., Obeso, J. A., Rdriguez-Oroz, M. C., 2012. Posterior parietooccipital hypometabolism may differentiate mild cognitive impairment from dementia in Parkinson’s disease. European Journal of Nuclear Medicine and Molecular Imaging 39 (11), 1767–1777.
(17) Teune, L. K., Bartels, A. L., de Jong, B. M.,Willemsen, A. T., Eshuis, S. A., de Vries, J. J., van Oostrom, J. C., LeendersK. L., 2010. Typical cerebral metabolic patterns in neurodegenerative brain diseases. Movement Disorders 25 (14), 2395–2404.
(18) Chang, C.-C., Lin, C.-J., 2011. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1–27:27, software available at http://www.csie.ntu.edu.tw/˜cjlin/libsvm.
(19) Hsu, C.-W., Lin, C.-J., 2002. A comparison of methods for multiclass support vector machines. Neural Networks, IEEE Transactions on 13 (2), 415–425.
(20) Biehl, M., 2015. A no-nonsense Matlab (TM) toolbox for GMLVQ. Software available at http://www.cs.rug. nl/biehl/gmlvq.html.
(21) Mudali, D., Biehl, M., Leenders, K. L., Roerdink, J. B. T. M., 2016. LVQ and SVM classification of FDG-PET brain data. In: et al., E. M. (Ed.), Advances in Self-Organizing Maps and Learning Vector Quantization. Proc. WSOM 2016, 11thWorkshop on Self-Organizing Maps. No. 428 in Advances in Intelligent Systems and Computing. Springer International Publishing Switzerland.
(22) Teune, L. K., Mudali, D., Renken, R. J., Jong, B. M. D., Segbers, M., Roerdink, J. B. T. M., Dierckx, R. A., Leenders, K. L., 2012. Glucose IMaging in ParkinsonismS. In: 16th International Congress of Parkinson’s Disease and Movement Disorders, Dublin, Ireland June 17-21. Abstract # 783.
