Estimation of Survival According to Body Mass Index (BMI), Hypertension, Diabetes and Heart Disease with Optimizable Decision Trees

Abstract

Non-communicable chronic diseases such as cardiovascular diseases and diabetes and the risk factors of these diseases are becoming an increasing health and development problem in the world. Non-communicable chronic diseases are among the most important causes of death according to the World Health Organization (WHO). The prediction of death or survival is very important in terms of contributing to scientific studies for the earlier diagnosis of non-communicable chronic diseases. Today's developing world, where technology and artificial intelligence can be used in every field, enables the prediction of survival in chronic diseases to be realized with many machine learning methods. In order to know which artificial intelligence or machine learning method is the most effective, it will be very useful to make applications with the methods used and even with the subclasses of the same method and to compare the classification results obtained from the applications with each other. In this study, survival in chronic diseases was estimated by using decision tree methods in four different structures designed by training with body mass index taken from individuals with chronic diseases and other hospital records. The highest accuracy rate was obtained with the optimizable decision trees (ODT) method, which is the simplest model among these models, which allows the most optimal selection of hyperparameters.

Keywords

• Survival
• Coarse
• Fine
• Medium
• Optimizable Decision Tree
• Body Mass Index

References

1. [1] B. Gupta, A. Rawat, A. Jain, A. Arora, N. Dhami, “Analysis of Various Decision Tree Algorithms for Classification in Data Mining”, International Journal of Computer Applications (0975 – 8887) Volume 163 – No 8, April 2017.
2. [2] S. J. Szydlowski, M. Luliak. Prevention of Disease-related Mortality from Chronic Non-communicable Diseases. CSWHI 2020; 11.2. 28 – 33; DOI: 10.22359/cswhi_11_2_06
3. [3] Z. Zhang, S. Jackson, R. Merritt, C. Gillespie, Q. Yang, “Association between cardiovascular health metrics and depression among U.S. adults: National Health and Nutrition Examination Survey”, Ann. Epidemiol. (2007-2014) 2019.
4. [4] D. C. Malta, B. B. Dunca, M. I. Schmidt, R. Teixeira, A.L.P. Ribeiro, M. S. Felisbino-Mendes et al. “Trends in mortality due to non-communicable diseases in the Brazilian adult population: national and subnational estimates and projections for 2030”. Popul Health Metr. 2020.18(Suppl 1).16.
5. [5] P. T. Istilli, L. H. Arroyo, R. A. Dias Lima et al. Premature mortality from chronic non-communicable diseases according to social vulnerability. Mundo da Saúde 2021,45: 187-194.
6. [6] C. F. Chien, L. F. Chen, “Data Mining to Improve Personnel Selection and Enhance Human Capital: A Case Study in High-Technology Industry,” Expert Systems with Applications, vol. 34, 2008, pp. 280-290
7. [7] S. Tsang, B. Kao, K. Y. Yip, Wai-Shing Ho, and S. D. Lee, “Decision Trees for Uncertain Data”, IEEE Transactions on Knowledge and Data Engineering, vol. 23. 1, January 2011.
8. [8] L. Rokach, O. Maimon, “Data Mining with Decision Trees Theory and Applications”, 2nd edition, volume 81, World Scientific Publishing Co. Pte. Ltd. April 2014.

9. [9] J. R, Quinlan. “C4.5: Programs for Machine Learning”, Morgan Kaufmann, San Mateo, CA, 302, 1993.
10. [10] G. Dougherty, “Pattern Recognition and Classification, Springer New York Heidelberg Dordrecht London”, first edition, DOI 10.1007/978-1-4614-5323-9
11. [11] WY. Loh and Yu-Shan Shih, “Split Selection Methods for Classification Trees, Statistica Sinica”, vol. 7. 4 (October 1997), pp. 815-840
12. [12] M. A. Friedl, C. E. Brodley, “Decision tree classification of land cover from remotely sensed data”, Remote Sensing of Environment, 61, 1997, 399–409
13. [13] S. R. Safavian, D. Landgrebe, “A survey of decision tree classifier methodology”, IEEE Transactions on Systems Man and Cybernetics, 21, 1991, 660-674
14. [14] PN. Tan, M. Steinbach, V. Kumar, “Introduction to Data Mining” (First Edition) (March 25, 2006) Copyright 2006, Pearson Addison-Wesley.
15. [15] O. Maimon, L. Rokach, “Data Mining and Knowledge Discovery Handbook” , Springer; 2nd ed. 2010.
16. [16] N. Suneetha, Ch. V. M. Hari, V. Sunil Kumar, “Modified Gini Index Classification: A Case Study of Heart Disease Dataset”, International Journal on Computer Science and Engineering Vol. 02, No. 06, 2010, 1959-1965
17. [17] L. Breiman, J.H. Friedman, R.A. Olshen and C. J. Stone. 1984, “Classification and Regression Trees” Monterey, CA: Wadsworth, 358
18. [18] L. E. Raileanu, and K. Stoffel, Theoretical Comparison between the Gini Index and Information Gain Criteria, Annals of Mathematics and Artificial Intelligence 41.1, 77-93. May 2004 
19. [19] K. Teknomo, “Decision Tree Tutorial”, Revoledu.com Online edition, Last Update: October 2012
20. [20] J. Mingers, “An empirical comparison of pruning methods for decision tree induction”, Machine Learning, 4, 1989, 227–243
21. [21] Z. Jingmin, et al. “Prediction model of in-hospital mortality in intensive care unit patients with heart failure: machine learning-based, retrospective analysis of the MIMIC-III database”, Dryad, Dataset, 2021, https://doi.org/10.5061/dryad.0p2ngf1zd.