Feature Selection Methods Applied to Severe Brain Damages Data
Wiesław Paja, Krzysztof Pancerz
DOI: http://dx.doi.org/10.15439/2017F382
Citation: Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 11, pages 199–202 (2017)
Abstract. Brain injuries seem to be one of the most widespread diseases. Hence, the main goal of our research was to investigate feature importance in the severe brain damages dataset according to the Glasgow Outcome Scale. This scale is recognized as one of several measures used to evaluate patients' functional ability as well as their conditions after applying brain damage therapy. The current approach is focused on an identification of a relevant subset of features with a similar influence on quality of classification models. According to the results gathered, about 12 from 42 descriptive features could be treated as important without the decrease of classification results.
References
- J. Wright. (2000) The disability rating scale. The Center for Outcome Measurement in Brain Injury. [Online]. Available: http:// www.tbims.org/ combi/drs
- P. B. Gorelick, M. Atler (2002) The prevention of stroke. CRC Press.
- K. M. Hall, T. Bushnik, B. Lakisic-Kazazic, J. Wright, and A. Cantagallo, “Assessing traumatic brain injury outcome measures for longterm follow-up of community-based individuals,” Archives of Physical Medicine and Rehabilitation, vol. 82, no. 3, pp. 367–374, 2001. http://dx.doi.org/10.1053/apmr.2001.21525
- L. Wilson, L. E. Pettigrew, and G. M. Teasdale, “Structured interviews for the Glasgow outcome scale and the extended Glasgow outcome scale: Guidelines for their use,” Journal of Neurotrauma, vol. 15, no. 8, pp. 573–585, 1998.
- J. Wilson, L. Pettigrew, and G. Teasdale, “Emotional and cognitive consequences of head injury in relation to the Glasgow outcome scale,” Journal of Neurology, Neurosurgery & Psychiatry, vol. 69, no. 2, pp. 204–209, 2000. http://dx.doi.org/10.1136/jnnp.69.2.204
- J. T. King, Jr., P.M. Carlier, and D.W. Marion, “Early Glasgow Outcome Scale Scores Predict Long-Term Functional Outcome in Patients with Severe Traumatic Brain Injury”, Journal of Neurotrauma. September, vol. 22, no. 9, pp. 947-954, 2005.
- J. W. Grzymała-Busse, Z. S. Hippe, T. Mroczek, W. Paja, and A. Bucinski, “A preliminary attempt to validation of Glasgow outcome scale for describing severe brain damages,” in Human-Computer Systems Interaction: Backgrounds and Applications, Z. S. Hippe and J.L. Kulikowski, Eds. Berlin Heidelberg: Springer, 2009, pp. 161–170.
- A. Bruno, N. Shah, C. Lin, B. Close, D. C. Hess, K. Davis, V. Baute, J. A. Switzer, J. L. Waller, and F. T. Nichols, “Improving modified Rankin Scale assessment with a simplified questionnaire,” Stroke, vol. 41, no. 5, pp. 1048–1050, 2010. http://dx.doi.org/10.1161/STROKEAHA.109. 571562
- B. Jennet and M. Bond, “Assessment of outcome after severe brain damage: A practical scale,” Lancet, vol. 1, pp. 480–484, 1975.
- S.E. Kasner, “Clinical interpretation and use of stroke scales,” The Lancet Neurology, vol. 5, no. 7, pp. 603–612, 2006.
- J. Lu et al., “A method for reducing misclassification in the extended Glasgow Outcome Score,” Journal of Neurotrauma, vol. 27, no. 5, pp. 843-852, 2010.
- A.D. Nichol et al. “Measuring Functional and Quality of Life Outcomes Following Major Head Injury: Common Scales and Checklists,” Injury, vol. 42, pp. 281-287, 2011. http://dx.doi.org/10.1016/j.injury.2010.11.047.
- W. R. Rudnicki, M. Wrzesien, and W. Paja, “All relevant feature selection methods and applications,” in Feature Selection for Data and Pattern Recognition, U. Stanczyk and L. C. Jain, Eds. Berlin Heidelberg: Springer, 2015, pp. 11–28. http://dx.doi.org/10.1007/978-3-662-45620-0_2
- H. Stoppiglia, G. Dreyfus, R. Dubois, and Y. Oussar, “Ranking a random feature for variable and feature selection,” Journal of Machine Learning Research, vol. 3, pp. 1399–1414, 2003.
- E. Tuv, A. Borisov, and K. Torkkola, “Feature selection using ensemble based ranking against artificial contrasts,” in Proceedings of the 2006 IEEE International Joint Conference on Neural Network, 2006. http://dx.doi.org/10.1109/IJCNN.2006.246991 pp. 2181–2186.
- W. Paja, “Feature selection methods based on decision rule and tree models,” in Intelligent Decision Technologies 2016: Proceedings of the 8th KES International Conference on Intelligent Decision Technologies (KES-IDT 2016) - Part II, I. Czarnowski, A. M. Caballero, R. J. Howlett, and L. C. Jain, Eds. Cham: Springer International Publishing, 2016, pp. 63–70. http://dx.doi.org/10.1007/978-3-319-39627-9_6
- J. Demsar et al., “Orange: Data mining toolbox in Python,” Journal of Machine Learning Research, vol. 14, pp. 2349–2353, 2013.
- T. Fawcett, “An introduction to ROC analysis,” Pattern Recognition Letters, vol. 27, no. 8, pp. 861–874, 2006. http://dx.doi.org/10.1016/j.patrec.2005. 10.010
- J. Hernández-Orallo, P. Flach, and C. Ferri, “A unified view of performance metrics: Translating threshold choice into expected classification loss,” Journal of Machine Learning Research, vol. 13, no. 1, pp. 2813–2869, 2012.
- A. Skowron and C. Rauszer, “The discernibility matrices and functions in information systems,” in Intelligent Decision Support: Handbook of Applications and Advances of the Rough Sets Theory, R. Słowinski, Ed. Dordrecht: Kluwer Academic Publishers, 1992, pp. 331–362. http://dx.doi.org/10.1007/978-94-015-7975-9_21
- Q. Shen and A. Chouchoulas, “A modular approach to generating fuzzy rules with reduced attributes for the monitoring of complex systems,” Engineering Applications of Artificial Intelligence, vol. 13, no. 3, pp. 263–278, 2000. http://dx.doi.org/10.1016/S0952-1976(00)00010-5