Prediction of Heart Failure Exitus with Machine Learning Classification Algorithms
Article Sidebar
Published
Dec 2, 2021
Main Article Content
Abstract
Aim: In this study, it is aimed to contribute to the artificial intelligence (AI) literature in the field of health and to the researchers who want to work in this field, by presenting the relevant theoretical infrastructure, with an application study on the estimation of heart failure mortality with ML classification algorithms.
Materials and Methods: In this study, ANN (artificial neural network), SVM (support vector machine), NB (naive bayes) classifier, KNN (k nearest neighbor), LR (logistic regression), DT (decision tree) and RF (random forest) algorithms, which are machine learning classification methods, were used to predict heart failure mortality. In order to increase the number of data, synthetic data derivation was applied. In addition, cross validation was applied to increase model accuracy. Model success was measured by confusion matrix and ROC AUC (Receiver Operating Characteristic, Area Under the Curve) score.
Results: In the practice study, it was determined that the risk factors for heart failure mortality were the duration of patient follow-up, ejection fraction, serum creatinine level and age of the patient. As a result of the application, 85.0% accuracy, 78.1% sensitivity, 88.2% specificity and 83.1% ROC AUC values were reached with Randım Forrest algorithm.
Discussion and Conclusion: In conclusion, it has been seen that the use of machine learning classification algorithms in the estimation of cardiac mortality has the potential to provide an important contribution to physicians as a decision support mechanism.
Materials and Methods: In this study, ANN (artificial neural network), SVM (support vector machine), NB (naive bayes) classifier, KNN (k nearest neighbor), LR (logistic regression), DT (decision tree) and RF (random forest) algorithms, which are machine learning classification methods, were used to predict heart failure mortality. In order to increase the number of data, synthetic data derivation was applied. In addition, cross validation was applied to increase model accuracy. Model success was measured by confusion matrix and ROC AUC (Receiver Operating Characteristic, Area Under the Curve) score.
Results: In the practice study, it was determined that the risk factors for heart failure mortality were the duration of patient follow-up, ejection fraction, serum creatinine level and age of the patient. As a result of the application, 85.0% accuracy, 78.1% sensitivity, 88.2% specificity and 83.1% ROC AUC values were reached with Randım Forrest algorithm.
Discussion and Conclusion: In conclusion, it has been seen that the use of machine learning classification algorithms in the estimation of cardiac mortality has the potential to provide an important contribution to physicians as a decision support mechanism.
Article Details
How to Cite
OSMANOGLU, Usame Omer; MUTLU, Fezan.
Prediction of Heart Failure Exitus with Machine Learning Classification Algorithms.
Journal of Multidisciplinary Developments, [S.l.], v. 6, n. 1, p. 74-82, dec. 2021.
ISSN 2564-6095.
Available at: <http://www.jomude.com/index.php/jomude/article/view/95>. Date accessed: 21 jan. 2025.
Section
Natural Sciences - Regular Research Paper
Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
References
Mitchell, T. M. (1997). Machine Learning. McGraw-Hill, New York. 2-3. ISBN: 0070428077.
Kepez, A., & Kabakçı, G. (2004). Kalp yetersizliği tedavisi. Acta Medica, 35(2), 69-81. (https://actamedica.org/index.php/actamedica/article/view/187)
Değertekin, M., Erol, Ç., Ergene, O., Tokgözoğlu, L., Aksoy, M., Erol, M. K., ... & Kozan, O. (2012). Heart failure prevalence and predictors in Turkey: HAPPY study. Turk Kardiyoloji Dernegi arsivi: Turk Kardiyoloji Derneginin yayin organidir, 40(4), 298-308. Doi: 10.5543/tkda.2012.65031 (https://europepmc.org/article/med/22951845)
Chicco, D., Jurman, G. (2020). Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone. BMC Medical Informatics and Decision Making 20, 16. Doi: 10.1186/s12911-020-1023-5
Osmanoglu, U. O. (2021). Prediction of heart failure mortality by machine learning classification algorithms. Ph.D. thesis, Eskisehir Osmangazi University.
Çelik, Ö., Aslan, A. F., Osmanoğlu, U. Ö., Çetin, N., & Tokar, B. (2020). Estimation of renal scarring in children with lower urinary tract dysfunction by utilizing resampling technique and machine learning algorithms. Journal of Surgery and Medicine, 4(7), 573-577. Doi: 10.28982/josam.691768 (http://jsurgmed.com/en/download/article-file/976184)
Github. (2020). https://github.com/scikit-learn-contrib/imbalanced-learn (Access Date: 21/10/2020)
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. Doi: 10.1613/jair.953 (https://www.jair.org/index.php/jair/article/view/10302/24590)
Python, (2012). General Python FAQ. Python Software Foundation. Licensed material. https://docs.python.org/3/faq/general.html (Access Date: 13.12.2014)
Osmanoğlu, U. Ö., Atak, O. N., Çağlar, K., Kayhan, H., & Can, T. C. (2020). Sentiment analysis for distance education course materials: A machine learning approach. Journal of Educational Technology and Online Learning, 3(1), 31-48. Doi: 10.31681/jetol.663733 (https://dergipark.org.tr/en/download/article-file/920037)
Stewart, M. (2019). The Actual Difference Between Statistics and Machine Learning. https://towardsdatascience.com/the-actual-difference-between-statistics-and-machine-learning-64b49f07ea3 (Access Date: 11.05.2021)
Lee, D. S., Stitt, A., Austin, P. C., Stukel, T. A., Schull, M. J., Chong, A., ... & Tu, J. V. (2012). Prediction of heart failure mortality in emergent care: a cohort study. Annals of Internal Medicine, 156(11), 767-775. Doi: 10.7326/0003-4819-156-11-201206050-00003 (10.7326/0003-4819-156-11-201206050-00003)
Austin, P. C., Tu, J. V., Ho, J. E., Levy, D., & Lee, D. S. (2013). Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes. Journal of Clinical Epidemiology, 66(4), 398-407. Doi: 10.1016/j.jclinepi.2012.11.008
Singh, J. S., Mordi, I. R., Vickneson, K., Fathi, A., Donnan, P. T., Mohan, M., ... & Lang, C. C. (2020). Dapagliflozin versus placebo on left ventricular remodeling in patients with diabetes and heart failure: the REFORM trial. Diabetes Care, 43(6), 1356-1359. Doi: 10.2337/dc19-2187
Asyalı, M. H. (2003). Discrimination power of long-term heart rate variability measures. In Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No. 03CH37439) (Vol. 1, pp. 200-203). IEEE.
Jovic, A., & Bogunovic, N. (2011). Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features. Artificial Intelligence in Medicine, 51(3), 175-186. Doi: 10.1016/j.artmed.2010.09.005
Mortazavi, B. J., Downing, N. S., Bucholz, E. M., Dharmarajan, K., Manhapra, A., Li, S. X., Negahban, S.N., Krumholz, H. M. (2016). Analysis of machine learning techniques for heart failure readmissions. Circulation: Cardiovascular Quality and Outcomes, 9(6), 629-640. Doi:10.1161/CIRCOUTCOMES.116.003039
Adler, E. D., Voors, A. A., Klein, L., Macheret, F., Braun, O. O., Urey, M. A., Zhu, W., Sama, I., Tadel, M., Campagnari, C., Greenberg, B., Yagil, A. (2020). Improving risk prediction in heart failure using machine learning. European journal of heart failure, 22(1), 139-147. Doi: 10.1002/ejhf.1628
Sun, J., Li, H., Fujita, H., Fu, B., & Ai, W. (2020). Class-imbalanced dynamic financial distress prediction based on Adaboost-SVM ensemble combined with SMOTE and time weighting. Information Fusion, 54, 128-144. Doi: 10.1016/j.inffus.2019.07.006
Kepez, A., & Kabakçı, G. (2004). Kalp yetersizliği tedavisi. Acta Medica, 35(2), 69-81. (https://actamedica.org/index.php/actamedica/article/view/187)
Değertekin, M., Erol, Ç., Ergene, O., Tokgözoğlu, L., Aksoy, M., Erol, M. K., ... & Kozan, O. (2012). Heart failure prevalence and predictors in Turkey: HAPPY study. Turk Kardiyoloji Dernegi arsivi: Turk Kardiyoloji Derneginin yayin organidir, 40(4), 298-308. Doi: 10.5543/tkda.2012.65031 (https://europepmc.org/article/med/22951845)
Chicco, D., Jurman, G. (2020). Machine learning can predict survival of patients with heart failure from serum creatinine and ejection fraction alone. BMC Medical Informatics and Decision Making 20, 16. Doi: 10.1186/s12911-020-1023-5
Osmanoglu, U. O. (2021). Prediction of heart failure mortality by machine learning classification algorithms. Ph.D. thesis, Eskisehir Osmangazi University.
Çelik, Ö., Aslan, A. F., Osmanoğlu, U. Ö., Çetin, N., & Tokar, B. (2020). Estimation of renal scarring in children with lower urinary tract dysfunction by utilizing resampling technique and machine learning algorithms. Journal of Surgery and Medicine, 4(7), 573-577. Doi: 10.28982/josam.691768 (http://jsurgmed.com/en/download/article-file/976184)
Github. (2020). https://github.com/scikit-learn-contrib/imbalanced-learn (Access Date: 21/10/2020)
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. Doi: 10.1613/jair.953 (https://www.jair.org/index.php/jair/article/view/10302/24590)
Python, (2012). General Python FAQ. Python Software Foundation. Licensed material. https://docs.python.org/3/faq/general.html (Access Date: 13.12.2014)
Osmanoğlu, U. Ö., Atak, O. N., Çağlar, K., Kayhan, H., & Can, T. C. (2020). Sentiment analysis for distance education course materials: A machine learning approach. Journal of Educational Technology and Online Learning, 3(1), 31-48. Doi: 10.31681/jetol.663733 (https://dergipark.org.tr/en/download/article-file/920037)
Stewart, M. (2019). The Actual Difference Between Statistics and Machine Learning. https://towardsdatascience.com/the-actual-difference-between-statistics-and-machine-learning-64b49f07ea3 (Access Date: 11.05.2021)
Lee, D. S., Stitt, A., Austin, P. C., Stukel, T. A., Schull, M. J., Chong, A., ... & Tu, J. V. (2012). Prediction of heart failure mortality in emergent care: a cohort study. Annals of Internal Medicine, 156(11), 767-775. Doi: 10.7326/0003-4819-156-11-201206050-00003 (10.7326/0003-4819-156-11-201206050-00003)
Austin, P. C., Tu, J. V., Ho, J. E., Levy, D., & Lee, D. S. (2013). Using methods from the data-mining and machine-learning literature for disease classification and prediction: a case study examining classification of heart failure subtypes. Journal of Clinical Epidemiology, 66(4), 398-407. Doi: 10.1016/j.jclinepi.2012.11.008
Singh, J. S., Mordi, I. R., Vickneson, K., Fathi, A., Donnan, P. T., Mohan, M., ... & Lang, C. C. (2020). Dapagliflozin versus placebo on left ventricular remodeling in patients with diabetes and heart failure: the REFORM trial. Diabetes Care, 43(6), 1356-1359. Doi: 10.2337/dc19-2187
Asyalı, M. H. (2003). Discrimination power of long-term heart rate variability measures. In Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No. 03CH37439) (Vol. 1, pp. 200-203). IEEE.
Jovic, A., & Bogunovic, N. (2011). Electrocardiogram analysis using a combination of statistical, geometric, and nonlinear heart rate variability features. Artificial Intelligence in Medicine, 51(3), 175-186. Doi: 10.1016/j.artmed.2010.09.005
Mortazavi, B. J., Downing, N. S., Bucholz, E. M., Dharmarajan, K., Manhapra, A., Li, S. X., Negahban, S.N., Krumholz, H. M. (2016). Analysis of machine learning techniques for heart failure readmissions. Circulation: Cardiovascular Quality and Outcomes, 9(6), 629-640. Doi:10.1161/CIRCOUTCOMES.116.003039
Adler, E. D., Voors, A. A., Klein, L., Macheret, F., Braun, O. O., Urey, M. A., Zhu, W., Sama, I., Tadel, M., Campagnari, C., Greenberg, B., Yagil, A. (2020). Improving risk prediction in heart failure using machine learning. European journal of heart failure, 22(1), 139-147. Doi: 10.1002/ejhf.1628
Sun, J., Li, H., Fujita, H., Fu, B., & Ai, W. (2020). Class-imbalanced dynamic financial distress prediction based on Adaboost-SVM ensemble combined with SMOTE and time weighting. Information Fusion, 54, 128-144. Doi: 10.1016/j.inffus.2019.07.006