Artificial Intelligence and Classification Algorithms in Heart Disease Data: Modern Approaches and Performance Comparison

Abstract

This study presents a data mining application aimed at investigating the prediction performance of classification algorithms on heart disease datasets. In this research, the likelihood of individuals having heart disease based on specific features was evaluated using various classification algorithms. The dataset used was created by John Moore's University in Liverpool, UK, and was last updated on June 6, 2020. The dataset consists of 1190 samples with 11 features. The study utilised several classification algorithms, including regression, k- nearest neighbours (KNN), Naive Bayes, random forest, decision trees, and support vector machines (SVM). All algorithms were implemented using the Python programming language and the Jupyter Notebook environment, and their classification performances were compared. The evaluation of success was based on metrics such as accuracy, sensitivity, specificity, and F1 score. According to the results, KNN, support vector machines, and random forest algorithms achieved the highest performance with an accuracy rate of 86.79%, outperforming the other algorithms. This study highlights the potential of classification algorithms in the early diagnosis of heart disease, emphasising the significance of artificial intelligence and data mining applications in the healthcare field.

Keywords

• Heart disease
• Artificial intelligence
• Data mining
• Performance comparison
• Classification algorithms.

Artificial Intelligence and Classification Algorithms In Heart Disease Data: Modern Approaches And Performance Comparison

Abstract

Bu çalışmada, sınıflandırma algoritmalarının kalp hastalıkları verilerindeki tahmin performansını incelemek amacıyla bir veri madenciliği uygulaması gerçekleştirilmiştir. Araştırma kapsamında, belirli özelliklere sahip bireylerin kalp hastalığı taşıma olasılığı, farklı sınıflandırma algoritmaları kullanılarak değerlendirilmiştir. Kullanılan veri kümesi, İngiltere Liverpool’daki John Moore's Üniversitesi tarafından oluşturulmuş ve son olarak 6 Haziran 2020 tarihinde güncellenmiştir. Veri kümesi, 11 özellikten oluşan 1190 örneği içermektedir. Çalışmada regresyon, k-en yakın komşu (KNN), Naive Bayes, rastgele orman, karar ağaçları ve destek vektör makineleri (SVM) algoritmaları kullanılmıştır. Tüm algoritmalar Python programlama dili ve Jupyter Notebook ortamında uygulanmış ve sınıflandırma performansları karşılaştırılmıştır. Başarı değerlendirmesi doğruluk oranı, duyarlılık, özgüllük ve F1 skoru gibi ölçütler üzerinden yapılmıştır. Elde edilen sonuçlara göre, KNN, destek vektör makineleri ve rastgele orman algoritmaları %86,79 doğruluk oranıyla diğer algoritmalara kıyasla en yüksek başarıyı göstermiştir. Bu çalışma, kalp hastalıklarının erken teşhisinde sınıflandırma algoritmalarının potansiyelini ortaya koyarak, sağlık alanında yapay zekâ ve veri madenciliği uygulamalarının önemini vurgulamaktadır.

Keywords

• Kalp hastalıkları
• Yapay zekâ
• Veri madenciliği
• Performans karşılaştırması
• Sınıflandırma algoritmaları.

References

1. Alan A, Karabatak M. Evaluation of Factors Affecting Performance in Data Set - Classification Relationship. Fırat University Müh. Bil. Journal. 2020.
2. Aydın S, Özkul AE. Data mining and an application in Anadolu University open education system. Journal of Education and Training Research. 2015.
3. Berry MJ, Linoff GS. Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management. Wiley. 2004.
4. Ergün K. Data Mining. Abdullah Baykal; [cited 2015 Dec 10]. Available from: http://abdullahbaykal.com.tr/verimaden.pdf.
5. Fayyad U, Piatetsky-Shapiro G, Smyth AP. From Data Mining to Knowledge Discovery in Databases. American Association for Artificial Intelligence. 2008.
6. Gürbüz F, Özbakır L, Yapıcı H. A Data Mining Application on Parts Removal Reports of an Airline Business in Turkey. Journal of Gazi University Faculty of Engineering and Architecture. 2013.
7. Hungarian Institute of Cardiology. Heart Disease. Budapest; 2017.
8. JavaPoint. Data Mining Techniques. [Internet]. 2011 [cited 2021 Mar 10]. Available from: https://www.javatpoint.com/data-mining-techniques.

9. Kalıkov A. Data Mining and an E-Commerce Application. PegemA; 2006.
10. Kaya M, Özel SA. Comparison of Open Source Data Mining Software. Academic Informatics. 2017.
11. Özekes S. Data Mining Models and Application Areas. Istanbul Commerce University Journal. 2003.
12. Park BH, Kargupta H. Distributed Data Mining: Algorithms, Systems, and Applications. CiteSeerx. 2002.
13. Ramageri MB. Data Mining Techniques and Applications. Indian Journal of Computer Science and Engineering. 2010.
14. Chollet F. Xception: Deep Learning with Depthwise Separable Convolutions. arXiv preprint arXiv:1610.02357. 2017.
15. Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018. p. 4510-20.
16. Tan M, Le QV. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In: International Conference on Machine Learning; 2019. p. 6105-14.
17. So-In C, Mongkonchai N, Aimtongkham P, Wijitsopon K, Rujirakul K. An evaluation of data mining classification models for network intrusion detection. In: Fourth International Conference on Digital Information and Communication Technology and its Applications (DICTAP); 2014.
18. Şengür D, Tekin A. Prediction of Graduation Grades of Students with Data Mining Methods. Journal of Information Technologies. 2014.
19. Rajak R. Deep Learning for Marble Defect Classification. Medium. 2022 Mar 20 [cited 2022 Mar 20]. Available from: https://rishirajak.medium.com/deep-learning-for-marble-defect-classification-f7928d077056.
20. Selver MA, Akay O. Feature Extraction for Quantitative Classification of Marbles. ResearchGate. 2007.
21. T.C. Ministry of Health. Turkish Society of Cardiology. [Internet]. 2015 [cited 2015 Oct 5]. Available from: https://tkd.org.tr/TKDData/Uploads/files/Turkiye-kalp-ve-damar-hastaliklari-onleme-ve-kontrol-programi.pdf.
22. He K, Zhang X, Ren S, Sun J. Identity mappings in deep residual networks. In: European Conference on Computer Vision; 2016. p. 630-45.
23. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A Simple Way to Prevent Neural Networks from Overfitting. The Journal of Machine Learning Research. 2014;15(1):1929-58.
24. Iandola FN, Han S, Moskewicz MW, Ashraf K, Dally WJ, Keutzer K. SqueezeNet: AlexNet-level Accuracy with 50x Fewer Parameters and <0.5MB Model Size. arXiv preprint arXiv:1602.07360. 2016.
25. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, et al. Mobilenets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv preprint arXiv:1704.04861. 2017.
26. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the Inception Architecture for Computer Vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 2818-26.
27. He K, Zhang X, Ren S, Sun J. Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition. In: European Conference on Computer Vision; 2015. p. 346-61.
28. Talend. Data Mining Techniques: The Complete List. [Internet]. 2020 [cited 2020 Jul 10]. Available from: https://www.talend.com/resources/data-mining-techniques/.
29. Taylor D. Data Mining Tutorial: What is | Process | Techniques & Examples. guru99. [Internet]. 2021 [cited 2021 Jan 8]. Available from: https://www.guru99.com/data-mining-tutorial.html#11.
30. Tekerek A. Data Mining Processes and Open Source Data Mining Tools. Academic Informatics. 2011.
31. Visa S, Ramsay B, Ralescu A, Knaap Ev. Confusion Matrix-based Feature Selection. Omnipress - Madison, WISCONSIN. 2011.
32. Waikato. Weka 3: Machine Learning Software in Java. [Internet]. 2017 [cited 2017 Mar 25]. Available from: https://www.cs.waikato.ac.nz/ml/weka/.