Farklı Sınıflandırıcılar ve Yeniden Örnekleme Teknikleri Kullanılarak Kalp Hastalığı Teşhisine Yönelik Karşılaştırmalı Bir Çalışma

Öz

Kalp hastalıkları dünya genelinde yaygın olarak görülmekte ve küresel ölümlerin üçte birlik kısmına neden olmaktadır. Kalp hastalığının semptomlarını ayırt etmedeki zorluk ve çoğu kalp hastasının kriz anına kadar semptomların farkında olmaması, hastalığın tanısını zorlaştırmaktadır. Bir yapay zekâ disiplini olan makine öğrenmesi bilinen verilerden yola çıkarak, yeni vakaların teşhisi konusunda uzmanlar için başarılı karar destek çözümleri sunmaktadır. Bu çalışmada kalp hastalıklarının erken teşhisine yönelik çeşitli makine öğrenmesi teknikleri kullanarak sınıflamalar gerçekleştirilmiştir. Çalışma literatürde yaygın olarak kullanılan UCI kalp hastalığı veri seti üzerinde gerçekleştirilmiştir. Sınıflandırma başarısını arttırmak için, eldeki veri setinin sınıf dengesini sağlamaya yönelik olarak yeniden örnekleme teknikleri kullanılmıştır. Naive Bayes, Karar Ağaçları, Destek Vektör Makinesi, K En yakın Komşu, Lojistik Regresyon, Rastgele Orman, AdaBoost ve CatBoost olmak üzere 8 farklı makine öğrenmesi tekniğinin her biri için örneklemesiz sınıflama yanında fazla örnekleme ve az örnekleme tekniklerinden 8 farklı yöntem kullanılarak toplam 72 sınıflandırma işlemi gerçekleştirilmiştir. Her bir sınıflandırma işleminin sonucu doğruluk, kesinlik, duyarlılık, F1 skoru ve AUC olmak üzere 5 farklı parametre ile raporlanmıştır. En yüksek doğruluk değeri Rastgele Orman ve InstanceHardnessThreshold az örnekleme tekniğinin kullanıldığı sınıflamada %98.46 olarak elde edilmiştir. Elde edilen ölçümlerin literatürde son yıllarda yapılan benzer çalışmalarda ulaşılan sonuçlardan daha yüksek olduğu görülmüştür.

Anahtar Kelimeler

• Kalp hastalığı teşhisi
• Makine öğrenmesi
• Yeniden örnekleme

A Comparative Study of Heart Disease Diagnosis using Various Classifiers and Resampling Techniques

Öz

Heart diseases are common worldwide and cause one-third of global deaths. The difficulty in distinguishing the symptoms of heart disease and the fact that most heart patients are not aware of the symptoms until the moment of crisis make the diagnosis of the disease difficult. Machine learning, an artificial intelligence discipline, provides experts with successful decision support solutions in diagnosing new cases based on known data. In this study, classifications were made using various machine learning techniques for the early diagnosis of heart diseases. The study was carried out on the UCI heart disease dataset, which is widely used in the literature. In order to increase the classification success, resampling techniques were used to ensure the class balance of the dataset. For each of 8 different machine learning techniques, namely Naive Bayes, Decision Trees, Support Vector Machine, K Nearest Neighbor, Logistic Regression, Random Forest, AdaBoost, and CatBoost, in addition to no-sampling classification, 8 different methods from oversampling and undersampling techniques were used to make a total of 72 classification processes were carried out. The result of each classification process is reported with 5 different parameters: accuracy, precision, recall, F1 score, and AUC. The highest accuracy value was obtained as 98.46% in the classification using Random Forest and InstanceHardnessThreshold undersampling technique. It was observed that the measurements obtained were higher than the results obtained in similar studies conducted in the literature in recent years.

Anahtar Kelimeler

• Heart disease diagnosis
• Machine learning
• Resampling

Kaynakça

1. Akalın, B., Veranyurt, Ü., Veranyurt, O., 2020. Classification of individuals at risk of heart disease using machine learning. Cumhuriyet Medical Journal 42, 283–289.
2. Ali, L., Niamat, A., Khan, J.A., Golilarz, N.A., Xingzhong, X., Noor, A., Nour, R., Bukhari, S.A.C., 2019a. An optimized stacked support vector machines based expert system for the effective prediction of heart failure. IEEE Access 7, 54007–54014.
3. Ali, L., Rahman, A., Khan, A., Zhou, M., Javeed, A., Khan, J.A., 2019b. An Automated Diagnostic System for Heart Disease Prediction Based on x2 Statistical Model and Optimally Configured Deep Neural Network. IEEE Access 7, 34938–34945. https://doi.org/10.1109/ACCESS.2019.2904800
4. Arabasadi, Z., Alizadehsani, R., Roshanzamir, M., Moosaei, H., Yarifard, A.A., 2017. Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm. Computer Methods and Programs in Biomedicine 141, 19–26. https://doi.org/10.1016/j.cmpb.2017.01.004
5. Asif, S., Wenhui, Y., Tao, Y., Jinhai, S., Jin, H., 2021. An Ensemble Machine Learning Method for the Prediction of Heart Disease, in: 2021 4th International Conference on Artificial Intelligence and Big Data (ICAIBD). IEEE, pp. 98–103.
6. Bharti, R., Khamparia, A., Shabaz, M., Dhiman, G., Pande, S., Singh, P., 2021. Prediction of Heart Disease Using a Combination of Machine Learning and Deep Learning. Computational Intelligence and Neuroscience 2021, 8387680. https://doi.org/10.1155/2021/8387680
7. Bilgin, G., 2021. Makine öğrenmesi algoritmaları kullanarak erken dönemde diyabet hastalığı riskinin araştırılması. Journal of Intelligent Systems: Theory and Applications, 4(1), 55-64.
8. Breiman, L., 2001. Random forests. Machine learning 45, 5–32.

9. Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P., 2002. SMOTE: synthetic minority over-sampling technique. Journal of artificial intelligence research 16, 321–357.
10. Das, R., Turkoglu, I., Sengur, A., 2009. Effective diagnosis of heart disease through neural networks ensembles. Expert Systems with Applications 36, 7675–7680. https://doi.org/10.1016/j.eswa.2008.09.013
11. David, H., Belcy, S.A., 2018. HEART DISEASE PREDICTION USING DATA MINING TECHNIQUES. ICTACT Journal on Soft Computing 9.
12. Dorogush, A.V., Ershov, V., Gulin, A., 2018. CatBoost: gradient boosting with categorical features support. CoRR abs/1810.11363.
13. Elhoseny, M., Mohammed, M.A., Mostafa, S.A., Abdulkareem, K.H., Maashi, Mashael S., Garcia-Zapirain, B., Mutlag, A.A., Maashi, Marwah Suliman, 2021. A new multi-agent feature wrapper machine learning approach for heart disease diagnosis. Comput. Mater. Contin 67, 51–71.
14. Fix, E., Hodges Jr, J.L., 1952. Discriminatory analysis-nonparametric discrimination: Small sample performance. California Univ Berkeley.
15. Freund, Y., Schapire, R.E., 1996. Experiments with a new boosting algorithm, in: Icml. Citeseer, pp. 148–156.
16. Haq, A.U., Li, J.P., Memon, M.H., Nazir, S., Sun, R., 2018. A hybrid intelligent system framework for the prediction of heart disease using machine learning algorithms. Mobile Information Systems 2018.
17. He, H., Bai, Y., Garcia, E., Li, S., 2008. ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning, in: Proceedings of the International Joint Conference on Neural Networks. pp. 1322–1328. https://doi.org/10.1109/IJCNN.2008.4633969
18. Heart Disease Data Set, UCI Machine Learning Repository [WWW Document], 1988. URL https://archive.ics.uci.edu/ml/datasets/Heart+Disease (erişim tarihi: 4.8.21).
19. Ho, T.K., 1995. Random decision forests, in: Proceedings of 3rd International Conference on Document Analysis and Recognition. IEEE, pp. 278–282.
20. Jabbar, M.A., Deekshatulu, B.L., Chandra, P., 2016. Prediction of Heart Disease Using Random Forest and Feature Subset Selection, in: Snášel, V., Abraham, A., Krömer, P., Pant, M., Muda, A.K. (Eds.), Innovations in Bio-Inspired Computing and Applications. Springer International Publishing, Cham, pp. 187–196.
21. Kartal, Mutlu, Köksal, Özlem, 2020. Akut Koroner Sendromlarda EKG.
22. Katarya, R., Meena, S.K., 2021. Machine learning techniques for heart disease prediction: a comparative study and analysis. Health and Technology 11, 87–97.
23. Kavitha, M., Gnaneswar, G., Dinesh, R., Sai, Y.R., Suraj, R.S., 2021. Heart Disease Prediction using Hybrid machine Learning Model, in: 2021 6th International Conference on Inventive Computation Technologies (ICICT). pp. 1329–1333. https://doi.org/10.1109/ICICT50816.2021.9358597
24. Kim, J.K., Kang, S., 2017. Neural Network-Based Coronary Heart Disease Risk Prediction Using Feature Correlation Analysis. Journal of Healthcare Engineering 2017, 2780501. https://doi.org/10.1155/2017/2780501
25. Kubat, M., Matwin, S., others, 1997. Addressing the curse of imbalanced training sets: one-sided selection, in: Icml. Citeseer, pp. 179–186.
26. Last, F., Douzas, G., Bacao, F., 2017. Oversampling for imbalanced learning based on k-means and smote. arXiv preprint arXiv:1711.00837.
27. Latha, C.B.C., Jeeva, S.C., 2019. Improving the accuracy of prediction of heart disease risk based on ensemble classification techniques. Informatics in Medicine Unlocked 16, 100203. https://doi.org/10.1016/j.imu.2019.100203
28. Laurikkala, J., 2001. Improving Identification of Difficult Small Classes by Balancing Class Distribution, in: Quaglini, S., Barahona, P., Andreassen, S. (Eds.), Artificial Intelligence in Medicine. Springer Berlin Heidelberg, Berlin, Heidelberg, pp. 63–66.
29. Liu, X., Wang, X., Su, Q., Zhang, M., Zhu, Y., Wang, Qiugen, Wang, Qian, 2017. A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method. Computational and Mathematical Methods in Medicine 2017, 8272091. https://doi.org/10.1155/2017/8272091
30. Maini, E., Venkateswarlu, B., Maini, B., Marwaha, D., 2021. Machine learning–based heart disease prediction system for Indian population: An exploratory study done in South India. Medical Journal Armed Forces India. https://doi.org/10.1016/j.mjafi.2020.10.013
31. Malav, A., Kadam, K., 2018. A hybrid approach for heart disease prediction using artificial neural network and K-means. International Journal of Pure and Applied Mathematics 118, 103–10.
32. Mienye, I.D., Sun, Y., Wang, Z., 2020. Improved sparse autoencoder based artificial neural network approach for prediction of heart disease. Informatics in Medicine Unlocked 18, 100307.
33. Miranda, E., Irwansyah, E., Amelga, A.Y., Maribondang, M.M., Salim, M., 2016. Detection of cardiovascular disease risk’s level for adults using naive Bayes classifier. Healthcare informatics research 22, 196–205.
34. Mohan, S., Thirumalai, C., Srivastava, G., 2019. Effective Heart Disease Prediction Using Hybrid Machine Learning Techniques. IEEE Access 7, 81542–81554. https://doi.org/10.1109/ACCESS.2019.2923707
35. Myers, K.D., Wilemon, K., McGowan, M.P., Howard, W., Staszak, D., Rader, D.J., 2021. COVID-19 associated risks of myocardial infarction in persons with familial hypercholesterolemia with or without ASCVD. American Journal of Preventive Cardiology 7, 100197. https://doi.org/10.1016/j.ajpc.2021.100197
36. Nguyen, H., Cooper, E., Kamei, K., 2011. Borderline over-sampling for imbalanced data classification. International Journal of Knowledge Engineering and Soft Data Paradigms 3, 4–21. https://doi.org/10.1504/IJKESDP.2011.039875
37. Poornima, V., Gladis, D., 2018. A novel approach for diagnosing heart disease with hybrid classifier. Biomed Res 29, 2274–2280.
38. Rajendran, N.A., Vincent, D.R., 2021. Heart Disease Prediction System using Ensemble of Machine Learning Algorithms. Recent Patents on Engineering 15, 130–139.
39. Rani, P., Kumar, R., Ahmed, N.M.S., Jain, A., 2021. A decision support system for heart disease prediction based upon machine learning. Journal of Reliable Intelligent Environments 1–13.
40. Smith, M.R., Martinez, T., Giraud-Carrier, C., 2014. An instance level analysis of data complexity. Machine Learning 95, 225–256. https://doi.org/10.1007/s10994-013-5422-z
41. Tama, B.A., Im, S., Lee, S., 2020. Improving an Intelligent Detection System for Coronary Heart Disease Using a Two-Tier Classifier Ensemble. BioMed Research International 2020, 9816142. https://doi.org/10.1155/2020/9816142
42. Terrada, O., Hamida, S., Cherradi, B., Raihani, A., Bouattane, O., 2020. Supervised machine learning based medical diagnosis support system for prediction of patients with heart disease. Advances in Science, Technology and Engineering Systems Journal 5, 269–277.
43. Tomek, I., 1976a. An Experiment with the Edited Nearest-Neighbor Rule. IEEE Transactions on Systems, Man, and Cybernetics SMC-6, 448–452. https://doi.org/10.1109/TSMC.1976.4309523
44. Tomek, I., 1976b. Two modifications of CNN. IEEE Trans. Syst. Man Cybern. 6, 769–772.
45. TUIK (Türkiye İstatistik Kurumu), 2021.Ölüm Nedeni İstatistikleri. URL http://www.tuik.gov.tr/PreHaberBultenleri.do?id=27620 (erişim tarihi: 5.18.21).
46. Vapnik, V., Golowich, S.E., Smola, A., others, 1997. Support vector method for function approximation, regression estimation, and signal processing. Advances in neural information processing systems 281–287.
47. Wiharto, W., Kusnanto, H., Herianto, H., 2016. Interpretation of clinical data based on C4. 5 algorithm for the diagnosis of coronary heart disease. Healthcare informatics research 22, 186–195.
48. WHO (World Health Organization), 2021. Global status report on noncommunicable diseases. URL https://www.who.int/news-room/fact-sheets/detail/noncommunicable-diseases (erişim tarihi: 6.21.21).