ASSESSMENT OF ASSOCIATIVE CLASSIFICATION APPROACH FOR PREDICTING MORTALITY BY HEART FAILURE

Abstract

Aim: This study aims to predict mortality status by heart failure and to determine the related factors by applying the relational classification method, one of the data mining methods, on the open-access heart failure data set. Materials and Methods: In this study, the associative classification model has been applied to the open-access data set named “Heart Failure Prediction”. The performance of the model was evaluated by accuracy, balanced accuracy, sensitivity, selectivity, positive predictive value, negative predictive value, and F1-score. Results: Accuracy, balanced accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score values obtained from the model were 0.866, 0.819, 0.688, 0.951, 0.868, 0.865 and 0.767 respectively. Conclusion: The findings obtained from this study showed that successful results were obtained in the study performed with the associative classification model on the heart failure data set. Also, certain rules regarding the disease to be used in preventive medicine practices were obtained with the proposed model.

Keywords

• Heart failure
• classification
• association rules
• relational classification

References

1. [1] P. Ponikowski, A. Voors, S. Anker, H. Bueno, J. Cleland, A. Coats, et al., "Authors/Task Force Members; Document Reviewers (2016) 2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure: The Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC). Developed with the special contribution of the Heart Failure Association (HFA) of the ESC," Eur J Heart Fail, vol. 18, pp. 891-975, 2016.
2. [2] G. Fonarow, K. Adams Jr, W. Abraham, C. Yancy, and W. Boscardin, "ADHERE Scientific Advisory Committee Study Group and Investigators. Risk stratification for in-hospital mortality in acutely decompensated heart failure: classification and regression tree analysis," Jama, vol. 293, pp. 572-80, 2005.
3. [3] M. B. Yılmaz, A. Çelik, Y. Çavuşoğlu, L. Bekar, E. Onrat, M. Eren, et al., "Snapshot evaluation of heart failure in Turkey: Baseline characteristics of SELFIE-TR," Turk Kardiyoloji Dernegi arsivi: Turk Kardiyoloji Derneginin yayin organidir, vol. 47, pp. 198-206, 2019.
4. [4] H. Akpınar, "Veri tabanlarında bilgi keşfi ve veri madenciliği," İstanbul Üniversitesi İşletme Fakültesi Dergisi, vol. 29, pp. 1-22, 2000.
5. [5] F. A. Thabtah, "A review of associative classification mining," Knowledge Engineering Review, vol. 22, pp. 37-65, 2007.
6. [6] D. Chicco and G. Jurman, "Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone," BMC Medical Informatics and Decision Making, vol. 20, p. 16, 2020/02/03 2020.
7. [7] U. M. Fayyad, G. Piatetsky-Shapiro, P. Smyth, and R. Uthurusamy, "Advances in knowledge discovery and data mining," 1996.
8. [8] D. T. Larose and C. D. Larose, Discovering knowledge in data: an introduction to data mining vol. 4: John Wiley & Sons, 2014.

9. [9] N. Ye, The handbook of data mining: CRC Press, 2003.
10. [10] F. Thabtah, "A review of associative classification mining," The Knowledge Engineering Review, vol. 22, pp. 37-65, 2007.
11. [11] G. S. Bleumink, A. M. Knetsch, M. C. Sturkenboom, S. M. Straus, A. Hofman, J. W. Deckers, et al., "Quantifying the heart failure epidemic: prevalence, incidence rate, lifetime risk and prognosis of heart failure: The Rotterdam Study," European heart journal, vol. 25, pp. 1614-1619, 2004.
12. [12] A. Mosterd and A. W. Hoes, "Clinical epidemiology of heart failure," Heart, vol. 93, pp. 1137-1146, 2007.
13. [13] İ. Perçın, F. H. Yağin, E. Güldoğan, and S. Yoloğlu, "ARM: An Interactive Web Software for Association Rules Mining and an Application in Medicine," in 2019 International Artificial Intelligence and Data Processing Symposium (IDAP), 2019, pp. 1-5.