IJSTR >> Volume 8 - Issue 12, December 2019 Edition

[Full Text]

AUTHOR(S)

Afreen Khan, Swaleha Zubair

KEYWORDS

alzheimer’s disease, classifier, ensemble, imputation, missing data, random forest

ABSTRACT

Objective: To evaluate and compare the performance of Random Forest (RF) ensemble classifier in imputation and non-imputation method of missing data values, and its impact to diagnose Alzheimer’s disease (AD) based on longitudinal MRI data. Method: We studied 373 MRI sessions involving 150 AD subjects aged 60 to 90 years [Mean age ± SD = 77.01 ± 7.64]. T1-weighted MRI of each subject on a 1.5-T Vision scanner were used for the image acquisition. The MRI dataset was taken from OASIS (Open Access Series of Imaging Studies) database. Based upon the MRI acquitted features in the dataset, we applied missing data imputation using RF ensemble to classify the subjects as demented or non-demented. We then compared them to determine which is more precise in the AD diagnosis Result: RF model-based imputation analysis outperforms with better accuracy than RF non-imputation method.

REFERENCES

[1] D. S. Marcus, A. F. Fotenos, J. G. Csernansky, J. C. Morris, and R. L. Buckner, “Open Access Series of Imaging Studies: Longitudinal MRI Data in Nondemented and Demented Older Adults,” J. Cogn. Neurosci., vol. 22, no. 12, pp. 2677–2684, 2010.
[2] E. Acuna and C. Rodriguez, “The Treatment of Missing Values and its Effect on Classifier Accuracy,” in Classification, Clustering, and Data Mining Applications, Springer, Berlin, Heidelberg, 2004, pp. 639–647.
[3] C. Patterson, “The state of the art of dementia research: New frontiers World Alzheimer Report 2018,” 2018.
[4] C. R. Jack et al., “Magnetic resonance imaging in Alzheimer ’ s Disease Neuroimaging Initiative 2,” Alzheimer’s Dement., vol. 11, no. 7, pp. 740–756, 2015.
[5] E. E. Bron, P. Boudewijn, F. Lelieveldt, M. Smits, and S. Klein, “Fast parallel image registration on CPU and GPU for diagnostic classification of Alzheimer’s disease,” Front. Neuroinform., vol. 7, no. January, pp. 1–15, 2014.
[6] F. Falahati, E. Westman, and A. Simmons, “Multivariate Data Analysis and Machine Learning in Alzheimer’s Disease with a Focus on Structural Magnetic Resonance Imaging,” J. Alzheimer’s Dis., vol. 41, pp. 685–708, 2014.
[7] D. Zhang and D. Shen, “Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer’s disease,” NeuroImage (Elsevier), vol. 59, no. 2, pp. 895–907, 2012.
[8] S. M. Stivaros, A. Gledson, G. Nenadic, X. Zeng, J. Keane, and A. Jackson, “Decision support systems for clinical radiological practice — towards the next generation,” Br. J. Radiol., vol. 83, pp. 904–914, 2010.
[9] A. Belle, M. A. Kon, and K. Najarian, “Biomedical Informatics for Computer-Aided Decision Support Systems: A Survey,” Sci. World J., 2013.
[10] B. H. Menze et al., “A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data,” BMC Bioinformatics, vol. 16, pp. 1–16, 2009.
[11] R. Caruana, “An Empirical Comparison of Supervised Learning Algorithms,” in Proceedings of the 23rd International Conference on Machine Learning, 2006.

[12] K. Lakshminarayan, S.A. Harp, T. Samad, Imputation of missing data in industrial databases, Appl. Intell. 11 (1999) 259–275.
[13] Y. Dong and C. J. Peng, “Principled missing data methods for researchers,” Springerplus, vol. 222, no. 2, pp. 1–17, 2013.
[14] A. Ozcift and A. Gulten, “Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms,” Comput. Methods Programs Biomed., vol. 104, no. 3, pp. 443–451, 2011.
[15] G. Biau, L. Devroye, G. Lugosi. “Consistency of random forests and other averaging classifiers.” Journal of Machine Learning Research, to appear, 2008.
[16] R. Polikar, A. Topalis, D. Parikh, D. Green, J. Frymiare, J. Kounios, C.M. Clark, An ensemble based data fusion approach for early diagnosis of Alzheimer’s disease, Inf. Fusion 9 (2008) 83–95.
[17] L. Breiman, Random forests, Mach. Learn. 45 (2001) 5–32.
[18] Y. Qi, J. Klein-Seetharaman, Z. Bar-Joseph. “Random forest similarity for protein-protein interaction prediction from multiple sources,” in Pacific Symposium on Biocomputing 10, pp. 531 - 542, 2005.

[19] T. K. Ho. “Random decision forests.” ICDAR ’95: Proceedings of the Third International Conference on Document Analysis and Recognition, Vol. 1, 1995.
[20] G. Ssali, T. Marwala. “Estimation of missing data using computational intelligence and decision trees.” Proceedings of IEEE International Joint Conference On Neural Networks, Hong Kong.
[21] N. J. Horton, K. P. Kleinman. “Much ado about nothing: a comparison of missing data methods and software to fit incomplete data regression models,” in The American Statistician, Vol. 61, No. 1, pp. 79, 2007.
[22] D. J. Fogarty. “Multiple imputation as a missing data approach to reject inference on consumer credit scoring.” http://interstat.statjournals.net/Year/2006/articles/0609001.pdf.
[23] M. Pampaka, G. Hutcheson, and J. Williams, “Handling missing data: analysis of a challenging data set using multiple imputation,” Int. J. Res. Method Educ., vol. 39, no. 1, pp. 19–37, 2016.