SUPPORT VECTOR MACHINES COMBINED WITH FEATURE SELECTION FOR DIABETES DIAGNOSIS

Abstract

Clinical Decision Support Systems (CDSS) are used as a service software which provides huge support to clinical decision making process where the main properties of a patient are matched to a tangible clinical knowledge. Within this gathered important information about patients, the medical decisions can be made more accurately. In this paper we present a CDSS that uses four physiological parameters of patients such as Pre-prandial Blood Glucose, Post-prandial Blood Glucose, Hemoglobin A1C (HbA1c) and Glucose in Urine to produce a prediction about the possibility of being diabetic. According to collected reference data provided from hospitals, the disease can be predicted by comparing the input data of patients. If the system cannot procure a prediction about patients’ status with these parameters, then the second phase which uses soft computing techniques is put into process with requesting additional data about patients. Our conducted experiments show that the diagnosis can be established in a breeze by getting the patients information with %80 accuracy. Support Vector Machines were applied to achieve maximum success rate with nine different physiological parameters such as; Pregnancy, glucose, blood pressure, skin fold, insulin, Hemoglobin A1C, body mass index, family tree and age. Four different Kernel Functions are implemented in case studies and classification process is optimized by reducing attributes with feature selection algorithms. This represents an improvement in classification of CDSS, while reducing computational complexity.

Keywords

• Decision Support System,Support Vector Machine,Sequential Forward Search,Feature Selection

References

1. [1] Barakat, N.; Bradley, A.P.; Barakat, M.N.H., "Intelligible Support Vector Machines for Diagnosis of Diabetes Mellitus," Information Technology in Biomedicine, IEEE Transactions on , vol.14, no.4, pp.1114,1120, July 2010
2. [2] UK Hypoglycaemia Study Group. "Risk of hypoglycaemia in types 1 and 2 diabetes: effects of treatment modalities and their duration." Diabetologia 50.6 (2007): 1140-1147.
3. [3] American Diabetes Association. "Diagnosis and classification of diabetes mellitus." Diabetes care 31.Supplement 1 (2008): S55-S60.
4. [4] Huxley, Rachel, Federica Barzi, and Mark Woodward. "Excess risk of fatal coronary heart disease associated with diabetes in men and women: meta-analysis of 37 prospective cohort studies." Bmj 332.7533 (2006): 73-78.
5. [5] Alavi, Maryam, and John C. Henderson. "An evolutionary strategy for implementing a decision support system." Management Science 27.11 (1981): 1309-1323.
6. [6] Kim, K. Kyu, and Jeffrey E. Michelman. "An examination of factors for the strategic use of information systems in the healthcare industry." MIS Quarterly (1990): 201-215.
7. [7] Hunt, Dereck L., et al. "Effects of computer-based clinical decision support systems on physician performance and patient outcomes: a systematic review." Jama 280.15 (1998): 1339-1346.
8. [8] Sim, I., Gorman, P., Greenes, R. A., Haynes, R. B., Kaplan, B., Lehmann, H., & Tang, P. C. (2001). Clinical decision support systems for the practice of evidence-based medicine. Journal of the American Medical Informatics Association, 8(6), 527-534.

9. [9] Kostic, P.; Vasiljevic, Z.; Pavlovic, S.; Milosavljevic, I.; Milanovic, J.G.; Blesic, S.; Milanovic, S., "Knowledge management system for clinical decision support — Application in cardiology," Telecommunications Forum (TELFOR), 2011 19th, pp.1261,1264, 22-24 Nov. 2011.
10. [10] Andres El-Fakdi, Francisco Gamero, Joaquim Meléndez, Vincent Auffret, and Pascal Haigron. 2014. eXiTCDSS: A framework for a workflow-based CBR for interventional Clinical Decision Support Systems and its application to TAVI. Expert Syst. Appl. 41, 2 (February 2014), 284-294.
11. [11] Kamaleswaran, R.; McGregor, C., "Integrating complex business processes for knowledge-driven clinical decision support systems," Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE , vol., no., pp.1306,1309, Aug. 28 2012-Sept. 1 2012.
12. [12] Reeda Kunhimangalam, Sujith Ovallath, and Paul K. Joseph. 2014. A Clinical Decision Support System with an Integrated EMR for Diagnosis of Peripheral Neuropathy. J. Med. Syst. 38, 4 (April 2014), 1-14.
13. [13] Shannon Standridge, Robert Faist, John Pestian, Tracy Glauser, and Richard Ittenbach. 2014. The Reliability of an Epilepsy Treatment Clinical Decision Support System. J. Med. Syst. 38, 10 (October 2014), 1-6.
14. [14] 14. Andrew King, Alex Roederer, Sanjian Chen, Nicholas Stevens, Philip Asare, Oleg Sokolsky, Insup Lee, Margaret Mullen-Fortino, and Soojin Park. 2010. Demo of the Generic Smart Alarm: a framework for the design, analysis, and implementation of smart alarms and other clinical decision support systems. In Wireless Health 2010 (WH '10). ACM, New York, NY, USA, 210-211.
15. [15] Juha Kemppinen, Jukka Korpela, Roce Partners, Kalle Elfvengren, Timo Salmisaari, Jussi Polkko, and Markku Tuominen. 2013. A Clinical Decision Support System for Adult ADHD Diagnostics Process. In Proceedings of the 2013 46th Hawaii International Conference on System Sciences (HICSS '13). IEEE Computer Society, Washington, DC, USA, 2616-2625.
16. [16] Shazia Karim and Imran Sarwar Bajwa. 2011. Clinical Decision Support System Based Virtual Telemedicine. In Proceedings of the 2011 Third International Conference on Intelligent Human-Machine Systems and Cybernetics - Volume 01 (IHMSC '11), Vol. 1. IEEE Computer Society, Washington, DC, USA, 16-21.
17. [17] Eren Gultepe, Hien Nguyen, Timothy Albertson, and Ilias Tagkopoulos. 2012. A Bayesian network for early diagnosis of sepsis patients: a basis for a clinical decision support system. In Proceedings of the 2012 IEEE 2nd International Conference on Computational Advances in Bio and medical Sciences (ICCABS '12). IEEE Computer Society, Washington, DC, USA, 1-5.
18. [18] Mattila, J.; Koikkalainen, J.; Virkki, A.; van Gils, M.; Lötjönen, J., "Design and Application of a Generic Clinical Decision Support System for Multiscale Data," Biomedical Engineering, IEEE Transactions on , vol.59, no.1, pp.234,240, Jan. 2012.
19. [19] The Rights of Patient Law (Numbered 23420,21th Clause) http://www.saglik.gov.tr/TR/belge/1-555/hasta-haklari-yonetmeligi.html
20. [20] International Expert Committee. "International Expert Committee report on the role of the A1C assay in the diagnosis of diabetes." Diabetes care 32.7 (2009): 1327-1334.
21. [21] El-Nabarawy, I.; Abdelbar, A.M.; Wunsch, D.C., "Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network," Neural Networks (IJCNN), The 2013 International Joint Conference on , pp.1,7, 4-9 Aug. 2013.
22. [22] Tai-cong Chen; Da-jian Han; Au, F.T.K.; Tham, L.G., "Acceleration of Levenberg-Marquardt training of neural networks with variable decay rate," Neural Networks, 2003. Proceedings of the International Joint Conference on , vol.3, no., pp.1873,1878 vol.3, 20-24 July 2003.
23. [23] Hannan Ma; Husheng Li, "Analysis of Frequency Dynamics in Power Grid: A Bayesian Structure Learning Approach," Smart Grid, IEEE Transactions on , vol.4, no.1, pp.457,466, March 2013.
24. [24] Yunong Zhang; Bingguo Mu; Huicheng Zheng, "Link Between and Comparison and Combination of Zhang Neural Network and Quasi-Newton BFGS Method for Time-Varying Quadratic Minimization," Cybernetics, IEEE Transactions on , vol.43, no.2, pp.490,503, April 2013.
25. [24] Moh, Y.; Buhmann, J.M., "Manifold regularization for semi-supervised sequential learning," Acoustics, Speech and Signal Processing, 2009. ICASSP 2009. IEEE International Conference on , vol., no., pp.1617,1620, 19-24 April 2009