Abstract
In the last decade, the progressive development of new machine learning schemas in combination with novel biomarkers have led us to more accurate models to diagnose and predict the evolution of neurological disorders like Parkinson’s Disease (PD). Though some of these previous work have attempted to combine multiple input data sources, many studies are critical of their lack of robustness when combining several input sources that with a high variability and/or not statistically significant. In order to minimize this problem, we have develop a Computer-Aided-Diagnosis (CAD) system for PD able to combine multiple input data sources underestimating those data types with poor classification rates and high variability. This model has been evaluated using FP-CIT SPECT and MRI images from healthy control subjects and patients with Parkinson’s Disease. As shown by our results, the cross-validation model proposed here does not only preserves the performance of our CAD system (93.8% of balanced accuracy) but also minimizes its variability even despite the input data sources poorly statistically significant.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Patients with parkinsonism labeled as SWEDD (Scan Without Evidence of Dopaminergic Deficit).
- 2.
Available at: ppmi-info.org/access-dataspecimens/download-data.
- 3.
Available at www.fil.ion.ucl.ac.uk/spm/software/spm12/.
- 4.
Arithmetic mean between sensitivity and specificity.
References
Augimeri, A., et al.: CADA—computer-aided DaTSCAN analysis. EJNMMI Phys. 3(1), 1–13 (2016). https://doi.org/10.1186/s40658-016-0140-9
Castillo-Barnes, D., et al.: Robust ensemble classification methodology for I123-Ioflupane SPECT images and multiple heterogeneous biomarkers in the diagnosis of Parkinson’s disease. Front. Neuroinform. 12, 53 (2018). https://doi.org/10.3389/fninf.2018.00053
Castillo-Barnes, D., et al.: Comparison between affine and non-affine transformations applied to I\(^{[123]}\)-FP-CIT SPECT images used for Parkinson’s disease diagnosis. In: Ferrández Vicente, J.M., Álvarez-Sánchez, J.R., de la Paz López, F., Toledo Moreo, J., Adeli, H. (eds.) IWINAC 2019, Part I. LNCS, vol. 11486, pp. 379–388. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-19591-5_39
Castillo-Barnes, D., et al.: Morphological characterization of functional brain imaging by isosurface analysis in Parkinson’s disease. Int. J. Neural Syst. 30(09), 2050044 (2020). https://doi.org/10.1142/s0129065720500446
Cigdem, O., Beheshti, I., Demirel, H.: Effects of different covariates and contrasts on classification of Parkinson’s disease using structural MRI. Comput. Biol. Med. 99, 173–181 (2018). https://doi.org/10.1016/j.compbiomed.2018.05.006
Górriz, J.M., et al.: Artificial intelligence within the interplay between natural and artificial computation: advances in data science, trends and applications. Neurocomputing 410, 237–270 (2020). https://doi.org/10.1016/j.neucom.2020.05.078
Hawkins, D.M.: The problem of overfitting. J. Chem. Inf. Comput. Sci. 44(1), 1–12 (2003). https://doi.org/10.1021/ci0342472
Hustad, E., Skogholt, A.H., Hveem, K., Aasly, J.O.: The accuracy of the clinical diagnosis of Parkinson disease. The HUNT study. J. Neurol. 265(9), 2120–2124 (2018). https://doi.org/10.1007/s00415-018-8969-6
Iarkov, A., Barreto, G.E., Grizzell, J.A., Echeverria, V.: Strategies for the treatment of Parkinson’s disease: beyond dopamine. Front. Aging Neurosci. 12, 4 (2020). https://doi.org/10.3389/fnagi.2020.00004
Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th International Joint Conference on Artificial Intelligence, IJCAI 1995, Quebec, Canada, vol. 2, pp. 1137–1145 (August 1995)
Martins, R., et al.: Automatic classification of idiopathic Parkinson’s disease and atypical parkinsonian syndromes combining [11c]raclopride PET uptake and MRI grey matter morphometry. J. Neural Eng. 18(4), 046037 (2021). https://doi.org/10.1088/1741-2552/abf772
Nicastro, N., et al.: Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal 123I-FP-CIT indices. J. Neurol. 266(7), 1771–1781 (2019). https://doi.org/10.1007/s00415-019-09330-z
Ramírez, J., et al.: Ensemble of random forests one vs. rest classifiers for MCI and AD prediction using ANOVA cortical and subcortical feature selection and partial least squares. J. Neurosci. Methods 302, 47–57 (2018). https://doi.org/10.1016/j.jneumeth.2017.12.005
Rokach, L.: Pattern Classification Using Ensemble Methods. World Scientific Publishing Company, Singapore (2009)
Salas-Gonzalez, D., et al.: Building a FP-CIT SPECT brain template using a posterization approach. Neuroinformatics 13(4), 391–402 (2015). https://doi.org/10.1007/s12021-015-9262-9
Salas-Gonzalez, D., et al.: Linear intensity normalization of FP-CIT SPECT brain images using the \(\alpha \)-stable distribution. NeuroImage 65, 449–455 (2013). https://doi.org/10.1016/j.neuroimage.2012.10.005
Salvatore, C., et al.: Machine learning on brain MRI data for differential diagnosis of Parkinson’s disease and progressive supranuclear palsy. J. Neurosci. Methods 222, 230–237 (2014). https://doi.org/10.1016/j.jneumeth.2013.11.016
Savica, R., et al.: Time trends in the incidence of Parkinson disease. JAMA Neurol. 73(8), 981 (2016). https://doi.org/10.1001/jamaneurol.2016.0947
Schoölkopf, B.: Learning with Kernels - Support Vector Machines, Regularization, Optimization, and Beyond. MIT Press, Cambridge (2002)
Segovia, F., et al.: Multivariate analysis of 18f-DMFP PET data to assist the diagnosis of parkinsonism. Front. Neuroinform. 11, 23 (2017). https://doi.org/10.3389/fninf.2017.00023
Shaw, R.G., Mitchell-Olds, T.: Anova for unbalanced data: an overview. Ecology 74(6), 1638–1645 (1993). https://doi.org/10.2307/1939922
Solana-Lavalle, G., Rosas-Romero, R.: Classification of PPMI MRI scans with voxel-based morphometry and machine learning to assist in the diagnosis of Parkinson’s disease. Comput. Methods Programs Biomed. 198, 105793 (2021). https://doi.org/10.1016/j.cmpb.2020.105793
Vlaar, A.M., et al.: Diagnostic value of 123i-ioflupane and 123i-iodobenzamide SPECT scans in 248 patients with parkinsonian syndromes. Eur. Neurol. 59(5), 258–266 (2008). https://doi.org/10.1159/000115640
Wingate, J., Kollia, I., Bidaut, L., Kollias, S.: Unified deep learning approach for prediction of Parkinson’s disease. IET Image Process. 14(10), 1980–1989 (2020). https://doi.org/10.1049/iet-ipr.2019.1526
Wold, S., Ruhe, A., Wold, H., W. J. Dunn, I.: The collinearity problem in linear regression. The partial least squares (PLS) approach to generalized inverses. SIAM J. Sci. Stat. Comput. 5(3), 735–743 (1984). https://doi.org/10.1137/0905052
Zhang, Y.D., et al.: Advances in multimodal data fusion in neuroimaging: overview, challenges, and novel orientation. Inf. Fusion 64, 149–187 (2020). https://doi.org/10.1016/j.inffus.2020.07.006
Acknowledgments
This work was supported by the MCIN/ AEI/10.13039/501100011033/ and FEDER “Una manera de hacer Europa”under the RTI2018-098913-B100 project; by the Consejería de Economía, Innovación, Ciencia y Empleo (Junta de Andalucía) and FEDER under CV20-45250, A-TIC-080-UGR18, B-TIC-586-UGR20 and P20-00525 projects; and by the Ministerio de Universidades under the FPU18/04902 grant given to C. Jimenez-Mesa and the Margarita-Salas grant to J.E. Arco.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Castillo-Barnes, D. et al. (2022). CAD System for Parkinson’s Disease with Penalization of Non-significant or High-Variability Input Data Sources. In: Ferrández Vicente, J.M., Álvarez-Sánchez, J.R., de la Paz López, F., Adeli, H. (eds) Artificial Intelligence in Neuroscience: Affective Analysis and Health Applications. IWINAC 2022. Lecture Notes in Computer Science, vol 13258. Springer, Cham. https://doi.org/10.1007/978-3-031-06242-1_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-06242-1_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-06241-4
Online ISBN: 978-3-031-06242-1
eBook Packages: Computer ScienceComputer Science (R0)