FUZZY LOGISTIC REGRESSION APPLICATION ON PREDICTIONS CORONARY HEART DISEASE

  • Vera Febriani 3Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Indonesia
  • Dian Lestari 3Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Indonesia
  • Sri Mardiyati 3Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Indonesia
  • Oktavia Lilyasari Department Cardiology and Vascular Medicine, Faculty of Medicine, Universitas Indonesia, Indonesia
DOI: https://doi.org/10.30598/barekengvol17iss1pp0571-0580
Keywords: Least Square, Fuzzy Logic, Mean Degree of Membership, Logistic Regression

Abstract

According to the World Health Organization (WHO) in 2015, 70% of cardiac deaths were caused by coronary heart disease (CHD). Based on WHO data in 2017, 17.5 million deaths were recorded, equivalent to 30% of the total deaths in the world caused by coronary heart disease. Coronary heart disease is a disorder of heart function caused by plaque that accumulates in arterial blood vessels so that it interferes with the supply of oxygen to the heart tissue. This causes reduced blood flow to the heart muscle and oxygen deficiency occurs. In more serious circumstances, it can result in a heart attack. Risk factors for coronary heart disease include age, gender, hypertension, cholesterol, heredity, diabetes mellitus, obesity, dyslipidemia, smoking and lack of physical activity. If a person's chances of suffering from coronary heart disease can be predicted early based on the existing risk factors, then the mortality rate of coronary heart disease can be suppressed. The objective of this study is to build a model that can predict the possibility of a patient suffering from coronary heart disease. The study used the Fuzzy Logistic Regression model. This model was used to maximize prediction results in which data size was limited. The least square method was used to estimate the value of the parameter. We obtained from National Cardiovascular Center Harapan Kita, Jakarta. Evaluation with the Mean Degree of Membership method showed that the model built was feasible and good enough to predict coronary heart disease. By using the confusion matrix, the accuracy of the prediction model is 80.00%, with a specificity of 42.85% and a sensitivity of 100%.

Downloads

Download data is not yet available.

References

Northside Hospital, “3 Risk factors for heart disease you can’t control-and 5 you can”. Available from https://northsidecvi.com/article-3-risk-factors-for-heart-disease-you-cant-control-and-5-you-can, [Accessed: June 10, 2022].

World Heart Federation, Cardiovascular Risk Factors. Available from https://world-heart-federation.org/world-heart-day/cvd-causes-conditions/risk-factors/, January 2022.

S. Palaniappan and R. Awang, “Intelligent heart disease prediction system using data mining techniques,” AICCSA 08 - 6th IEEE/ACS Int. Conf. Comput. Syst. Appl., pp. 108–115, 22 April 2008, doi: 10.1109/AICCSA.2008.4493524.

M. A. Nishara Banu and B. Gomathy, “Disease forecasting system using data mining methods,” Proceedings - 2014 International Conference on Intelligent Computing Applications, ICICA 2014, pp. 130–133. https://doi.org/10.1109/ICICA.2014.36, 2014.

V. Febriani, D. Lestari, S. Mardiyati, and S. Devila, “Predicting readmission risk after coronary artery bypass graft surgery using logistic regression model,” in J. Phys. Conf. Ser., vol. 1725, no. 1, 2021, doi: 10.1088/1742-6596/1725/1/012083.

H. Ayatollahi, L. Gholamhosseini, and M. Salehi, “Predicting coronary artery disease: A comparison between two data mining algorithms”, BMC Public Health, 19:448, April 2019, doi: 10.1186/s12889-019-6721-5.

A. H. Gonsalves, F. Thabtah, R. M. A. Mohammad, and G. Singh, “Prediction of coronary heart disease using machine learning: An experimental analysis,” Proceedings of ICDLT 2019: 2019 3rd International Conference on Deep Learning Technologies, 5 July 2019, doi: 10.1145/3342999.3343015.

P. I. Aaronson, and J. P. T. Ward, At a Glance: Sistem Kardiovaskular, 3th ed, Jakarta: Penerbit Erlangga, 2010.

T. R. Barbeau, Cardiovascular physiology. Florence: Francis Marion University, 2004.

S. Agarwal, C. Schechter, A. Zaman, “Assessment of functional status and quality of life after percutaneous coronary revascularization in octogenarians,” Age and Ageing, Vol. 38, Issue 6, pp. 748-751, November 2009. https://doi.org/10.1093/ageing/afp174.

H. H. Gray, K. D. Dawkins, J. M. Morgan, and I. A. Simpson, Lecture Notes: Kardiologi, 4th ed., Jakarta: Erlangga, 2005.

R. Shoufiah. “Hubungan Faktor Resiko dan Karakteristik Penderita dengan Kejadian Penyakit Jantung Koroner,” Mahakam Nursing Journal, Vol 1, No. 1, pp. 17-26, Mei 2016.

I. Soeharto, Pencegahan Dan Penyembuhan Penyakit Jantung Koroner, Jakarta: Gramedia Pustaka Utama, 2001.

A. F. Yahya, Menaklukkan Pembunuh no.1: Mencegah dan Mengatasi Penyakit Jantung Koroner Secara Tepat, Bandung: PT Mizan Pustaka, 2010.

D. S. Borowiak, and A. F. Saphiro, Financial and Actuarial Statistics: An Introduction, 2nd ed. New York: Chapman and Hall/CRC, 2020.

L. A. Zadeh, Fuzzy sets. Information and control. Vol. 8, pp. 338-353, 1965.

R. M. Dom, B. Abidin, S. A. Kareem, S. M. Ismail, and N. M. Daud, “Determining the critical success factors of oral cancer susceptibility prediction in Malaysia using fuzzy models,” Sains Malaysiana, vol. 41, no. 5, pp. 633–640, 2012.

S. Pourahmad, S. M. T. Ayatollahi, and S. M. Taheri, “Fuzzy logistic regression: A new possibilistic model and its application in clinical vague status,” Iran. J. Fuzzy Syst., vol. 8, no. 1, pp. 1–17, 2011.

N. Y. Pehlivan and A. Sahin, “An Integrated approach for fuzzy logistic regression,” İstatistikçiler Dergisiİstatistik ve Aktüerya, vol. 11, no. 1, pp. 42–54, 2018.

S. Pourahmad, S. M. T. Ayatollahi, S. M. Taheri, and Z. H. Agahi, “Fuzzy logistic regression based on the least squares approach with application in clinical studies,” Comput. Math. with Appl., vol. 62, no. 9, pp. 3353–3365, 2011, doi: 10.1016/j.camwa.2011.08.050.

J. Mohammadi and S. M. Taheri, “Pedomodels fitting with fuzzy least squares regression,” Iran. J. Fuzzy Syst., vol. 1, no. 2, pp. 45–61, 2004.

D. W. Hosmer and S. Lemeshow, Applied Logistic Regression, second ed, New York: John Wiley and Sons, 2000.

H. Tanaka, S. Uejima, and K. Asai, “Linear Regression Analysis with Fuzzy Model”, IEEE Transactions on Systems, Man and Cybernetics, Vol: 12, Issue: 6, November 1982, page: 903-907.

http://dx.doi.org/10.1109/TSMC.1982.4308925.

D. C. Montgomery, Introduction to Linear Regression Analysis, 5th ed., USA: John Wiley & sons, Inc, 2012.

W. Mendenhall, and T. Sincich, A Second Course in Statistics: Regression Analysis, 7th ed., Boston: Pearson Education Limited, 2012.

B. S. Gildeh, and D. Gien, A goodness of fit index to reliability analysis in fuzzy model. Advances in Intelligent Systems, Fuzzy Systems, Evolutionary Computation: 78-83, 2002.

B. Ratner, Statistical and machine-learning data mining, 3rd ed., Boca Raton: CRC Press, 2017.

Published
2023-04-20
How to Cite
[1]
V. Febriani, D. Lestari, S. Mardiyati, and O. Lilyasari, “FUZZY LOGISTIC REGRESSION APPLICATION ON PREDICTIONS CORONARY HEART DISEASE”, BAREKENG: J. Math. & App., vol. 17, no. 1, pp. 0571-0580, Apr. 2023.
Issue
Vol 17 No 1 (2023): BAREKENG: Journal of Mathematics and Its Applications
Section
Articles

Copyright (c) 2023 Vera Febriani, Dian Lestari, Sri Mardiyati, Oktavia Lilyasari

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this Journal agree to the following terms:

  1. Author retain copyright and grant the journal right of first publication with the work simultaneously licensed under a creative commons attribution license that allow others to share the work within an acknowledgement of the work’s authorship and initial publication of this journal.
  2. Authors are able to enter into separate, additional contractual arrangement for the non-exclusive distribution of the journal’s published version of the work (e.g. acknowledgement of its initial publication in this journal).
  3. Authors are permitted and encouraged to post their work online (e.g. in institutional repositories or on their websites) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published works.