Topluluk Makine Öğrenmesi Algoritmaları ile Koroner Arter Hastalığının Uzun Dönem Tahmini

Öz

Koroner arter hastalığı (KAH) dünya çapında önde gelen ölüm nedenidir ve bu nedenle invaziv olmayan, maliyet etkin ve güvenilir erken tespit yöntemlerine ihtiyaç duyulmaktadır. Bu çalışmada, KAH'nın tahmininde çeşitli makine öğrenimi (ML) modellerinin etkinliği değerlendirildi ve Sınıf Dengesizliğinin Üstesinden Gelme Yöntemi (SMOTE) kullanılarak sınıf dengesizliğine odaklanıldı. Framingham KAH veri seti kullanılarak SMOTE, verileri dengelemek için farklı k-değerleri ile uygulandı ve tahmin performansına etkisi incelendi. Ön işleme sırasında belirlenen sekiz önemli özellik—yaş, diyastolik kan basıncı (diaBP), glukoz, kalp hızı, sistolik kan basıncı (sysBP), toplam kolesterol (totChol), günlük sigara sayısı (cigsPerDay) ve vücut kitle indeksi (BMI)—daha ileri analizler için kullanıldı. Test edilen modeller arasında, StackingC sınıflandırıcısı üstün performans göstererek k=1 için %95.81 doğruluk, %95.9 duyarlılık, %95.7 özgüllük ve %99.2 AUROC elde etti. Bu bulgular, StackingC modelinin KAH tahmininde sağlam bir araç olarak potansiyelini vurgulamakta ve erken teşhis için umut verici invaziv olmayan bir yöntem sunmaktadır.

Anahtar Kelimeler

• Makine öğrenmesi
• koroner arter hastalığı tahmini
• sınıf dengesizliği
• SMOTE
• stackingC sınıflandırıcı

Long-Term Prediction of Coronary Artery Disease via Ensemble Machine Learning Algorithms

Abstract

Coronary artery disease (CAD) is the leading cause of death worldwide, necessitating early detection methods that are non-invasive, cost-effective, and reliable. In this study, the effectiveness of various machine learning (ML) models in predicting CAD was evaluated, with a focus on addressing class imbalance using the Synthetic Minority Oversampling Technique (SMOTE). The Framingham CAD dataset was utilized, and SMOTE was applied with different k-values to balance the data, examining the impact on prediction performance. Eight significant features—age, diaBP, glucose, heart rate, sysBP, totChol, cigsPerDay, and BMI—were determined during preprocessing and used for further analysis. Among the models tested, the StackingC classifier demonstrated superior performance, achieving an accuracy of 95.81%, sensitivity of 95.9%, specificity of 95.7%, and an AUROC of 99.2% for k=1. These findings highlight the potential of the StackingC model as a robust tool for CAD prediction, offering a promising non-invasive method for early diagnosis.

Keywords

• Machine learning
• coronary artery disease prediction
• class imbalance
• SMOTE
• stackingC classifier.

References

1. [1] World Health Organization, “The top 10 causes of death,” Jun. 09, 2024. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/the-top-10-causes-of-death
2. [2] R. Alizadehsani et al., “Machine learning-based coronary artery disease diagnosis: A comprehensive review,” Comput. Biol. Med., vol. 111, p. 103346, Aug. 2019, doi: 10.1016/j.compbiomed.2019.103346.
3. [3] S. Kutiame, R. Millham, A. F. Adekoya, M. Tettey, B. A. Weyori, and P. Appiahene, “Application of Machine Learning Algorithms in Coronary Heart Disease: A Systematic Literature Review and Meta-Analysis,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 6, 2022, doi: 10.14569/IJACSA.2022.0130620.
4. [4] I. Kurt, M. Ture, and A. T. Kurum, “Comparing performances of logistic regression, classification and regression tree, and neural networks for predicting coronary artery disease,” Expert Syst. Appl., vol. 34, no. 1, pp. 366–374, Jan. 2008, doi: 10.1016/j.eswa.2006.09.004.
5. [5] I. Babaoğlu, O. Fındık, and M. Bayrak, “Effects of principle component analysis on assessment of coronary artery diseases using support vector machine,” Expert Syst. Appl., vol. 37, no. 3, pp. 2182–2185, Mar. 2010, doi: 10.1016/j.eswa.2009.07.055.
6. [6] R. Alizadehsani et al., “A data mining approach for diagnosis of coronary artery disease,” Comput. Methods Programs Biomed., vol. 111, no. 1, pp. 52–61, Jul. 2013, doi: 10.1016/j.cmpb.2013.03.004.
7. [7] S. Akila and S. Chandramathi, “A Hybrid Method for Coronary Heart Disease Risk Prediction using Decision Tree and Multi Layer Perceptron,” Indian J. Sci. Technol., vol. 8, no. 34, Dec. 2015, doi: 10.17485/ijst/2015/v8i34/85947.
8. [8] Y.-T. Lo, H. Fujita, and T.-W. Pai, “PREDICTION OF CORONARY ARTERY DISEASE BASED ON ENSEMBLE LEARNING APPROACHES AND CO-EXPRESSED OBSERVATIONS,” J. Mech. Med. Biol., vol. 16, no. 01, p. 1640010, Feb. 2016, doi: 10.1142/S0219519416400108.

9. [9] K. H. Miao, J. H., and G. J., “Diagnosing Coronary Heart Disease using Ensemble Machine Learning,” Int. J. Adv. Comput. Sci. Appl., vol. 7, no. 10, 2016, doi: 10.14569/IJACSA.2016.071004.
10. [10] R. Alizadehsani et al., “Coronary artery disease detection using computational intelligence methods,” Knowl.-Based Syst., vol. 109, pp. 187–197, Oct. 2016, doi: 10.1016/j.knosys.2016.07.004.
11. [11] H. Forssen, R. Patel, N. Fitzpatrick, A. Timmis, H. Hemingway, and S. Denaxas, “Evaluation of Machine Learning Methods to Predict Coronary Artery Disease Using Metabolomic Data”.
12. [12] J.-J. Beunza et al., “Comparison of machine learning algorithms for clinical event prediction (risk of coronary heart disease),” J. Biomed. Inform., vol. 97, p. 103257, Sep. 2019, doi: 10.1016/j.jbi.2019.103257.
13. [13] M. Abdar, W. Książek, U. R. Acharya, R.-S. Tan, V. Makarenkov, and P. Pławiak, “A new machine learning technique for an accurate diagnosis of coronary artery disease,” Comput. Methods Programs Biomed., vol. 179, p. 104992, Oct. 2019, doi: 10.1016/j.cmpb.2019.104992.
14. [14] K. R. Dahal and Y. Gautam, “Argumentative Comparative Analysis of Machine Learning on Coronary Artery Disease,” Open J. Stat., vol. 10, no. 04, pp. 694–705, 2020, doi: 10.4236/ojs.2020.104043.
15. [15] I. C. Dipto, T. Islam, H. M. M. Rahman, and M. A. Rahman, “Comparison of Different Machine Learning Algorithms for the Prediction of Coronary Artery Disease,” J. Data Anal. Inf. Process., vol. 08, no. 02, pp. 41–68, 2020, doi: 10.4236/jdaip.2020.82003.
16. [16] A. Dutta, T. Batabyal, M. Basu, and S. T. Acton, “An efficient convolutional neural network for coronary heart disease prediction,” Expert Syst. Appl., vol. 159, p. 113408, Nov. 2020, doi: 10.1016/j.eswa.2020.113408.
17. [17] J. H. Joloudari et al., “Coronary Artery Disease Diagnosis; Ranking the Significant Features Using a Random Trees Model,” Int. J. Environ. Res. Public. Health, vol. 17, no. 3, p. 731, Jan. 2020, doi: 10.3390/ijerph17030731.
18. [18] L. J. Muhammad, I. Al-Shourbaji, A. A. Haruna, I. A. Mohammed, A. Ahmad, and M. B. Jibrin, “Machine Learning Predictive Models for Coronary Artery Disease,” SN Comput. Sci., vol. 2, no. 5, p. 350, Sep. 2021, doi: 10.1007/s42979-021-00731-4.
19. [19] C. Wang et al., “Development and Validation of a Predictive Model for Coronary Artery Disease Using Machine Learning,” Front. Cardiovasc. Med., vol. 8, p. 614204, Feb. 2021, doi: 10.3389/fcvm.2021.614204.
20. [20] J. Wang, C. Rao, M. Goh, and X. Xiao, “Risk assessment of coronary heart disease based on cloud-random forest,” Artif. Intell. Rev., vol. 56, no. 1, pp. 203–232, Jan. 2023, doi: 10.1007/s10462-022-10170-z.
21. [21] N. Masih, H. Naz, and S. Ahuja, “Multilayer perceptron based deep neural network for early detection of coronary heart disease,” Health Technol., vol. 11, no. 1, pp. 127–138, Jan. 2021, doi: 10.1007/s12553-020-00509-3.
22. [22] M. Trigka and E. Dritsas, “Long-Term Coronary Artery Disease Risk Prediction with Machine Learning Models,” Sensors, vol. 23, no. 3, p. 1193, Jan. 2023, doi: 10.3390/s23031193.
23. [23] S. Saeedbakhsh, M. Sattari, M. Mohammadi, J. Najafian, and F. Mohammadi, “Diagnosis of coronary artery disease based on machine learning algorithms support vector machine, artificial neural network, and random forest,” Adv. Biomed. Res., vol. 12, no. 1, p. 51, 2023, doi: 10.4103/abr.abr_383_21.
24. [24] A. A. Huang and S. Y. Huang, “Use of machine learning to identify risk factors for coronary artery disease,” PLOS ONE, vol. 18, no. 4, p. e0284103, Apr. 2023, doi: 10.1371/journal.pone.0284103.
25. [25] F. Özbilgin, Ç. Kurnaz, and E. Aydın, “Prediction of Coronary Artery Disease Using Machine Learning Techniques with Iris Analysis,” Diagnostics, vol. 13, no. 6, p. 1081, Mar. 2023, doi: 10.3390/diagnostics13061081.
26. [26] F. Li, Y. Chen, and H. Xu, “Coronary heart disease prediction based on hybrid deep learning,” Rev. Sci. Instrum., vol. 95, no. 1, p. 015115, Jan. 2024, doi: 10.1063/5.0172368.
27. [27] “The Framingham CAD dataset.” Accessed: Jun. 10, 2024. [Online]. Available: https://www.kaggle.com/datasets/navink25/framingham
28. [28] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, Jun. 2002, doi: 10.1613/jair.953.
29. [29] D. W. Aha, D. Kibler, and M. K. Albert, “Instance-based learning algorithms,” Mach. Learn., vol. 6, no. 1, pp. 37–66, Jan. 1991, doi: 10.1007/BF00153759.
30. [30] L. Breiman, “Random Forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
31. [31] M. Friedman, “The Use of Ranks to Avoid the Assumption of Normality Implicit in the Analysis of Variance,” J. Am. Stat. Assoc., vol. 32, no. 200, pp. 675–701, Dec. 1937, doi: 10.1080/01621459.1937.10503522.
32. [32] J. G. Cleary and L. E. Trigg, “K*: An Instance-based Learner Using an Entropic Distance Measure,” in Machine Learning Proceedings 1995, Elsevier, 1995, pp. 108–114. doi: 10.1016/B978-1-55860-377-6.50022-0.
33. [33] D. H. Wolpert, “Stacked generalization,” Neural Netw., vol. 5, no. 2, pp. 241–259, Jan. 1992, doi: 10.1016/S0893-6080(05)80023-1.
34. [34] A. Seewald, How to Make Stacking Better and Faster While Also Taking Care of an Unknown Weakness. 2002, p. 561.