Early-stage heart failure disease prediction with deep learning approach

Year 2023, Issue: 055, 34 - 49, 31.12.2023

Emin Demir , Ferhat Bozkurt , Yusuf Ziya Ayık

https://doi.org/10.59313/jsr-a.1341663

Abstract

Cardiovascular diseases rank the highest among diseases in terms of mortality rate and cause millions of deaths every year. Heart failure is a type of cardiovascular disease and its early diagnosis is extremely important for its prevention. It may be vitally important to understand to what extent which body values, characteristics and factors (age, gender, blood pressure, sugar, etc.) affect this disease and to predict whether the individual will have a possible heart attack in the future. In this study, firstly, the correlation level of the relevant body values with the disease is extracted and in the second stage, a method that predicts heart attack with DNN (Deep Neural Network) and CNN (Convolutional Neural Network) deep learning models is proposed. In the study, 918 observations obtained from the kaggle site were used. Firstly, missing data, categorical data, non-numerical features were checked. Then, outliers were cleaned and the relationship of the features in the dataset with the disease state was revealed by feature engineering operations on the data. Finally, deep neural network models were built and the model was trained and hyperparameter adjustment was performed with GridSearhCV to achieve the highest success rate. As a result of the study, Accuracy, Precision, Recall and F1-Score values were found as 0.9375, 0.9629, 0.9176, 0.9397 for DNN and 0.9312, 0.9512, 0.9176, 0.9340 for CNN respectively. The AUC value calculated from the ROC curve was found to be equal to 0.96 in both deep learning models.

Keywords

Deep learning, DNN, CNN, Heart attack prediction

References

• [1] J. H. Brice, J. K. Griswell, T. R. Delbridge, and C. B. Key, “Stroke: from recognition by the public to management by emergency medical services,” Prehosp Emerg Care, vol. 6, no. 1, pp. 99–106, 2002, doi: 10.1080/10903120290938904.
• [2] M. H. Park et al., “No difference in stroke knowledge between Korean adherents to traditional and western medicine – the AGE study: an epidemiological study,” BMC Public Health, vol. 6, no. 1, p. 153, Jun. 2006, doi: 10.1186/1471-2458-6-153.
• [3] M. H. Fazel Zarandi, A. Seifi, M. M. Ershadi, and H. Esmaeeli, “An expert system based on fuzzy bayesian network for heart disease diagnosis,” in Fuzzy Logic in Intelligent System Design, P. Melin, O. Castillo, J. Kacprzyk, M. Reformat, and W. Melek, Eds., in Advances in Intelligent Systems and Computing. Cham: Springer International Publishing, 2018, pp. 191–201. doi: 10.1007/978-3-319-67137-6_21.
• [4] H. Yan, Y. Jiang, J. Zheng, C. Peng, and Q. Li, “A multilayer perceptron-based medical decision support system for heart disease diagnosis,” Expert Systems with Applications, vol. 30, no. 2, pp. 272–281, Feb. 2006, doi: 10.1016/j.eswa.2005.07.022.
• [5] R. Das, I. Turkoglu, and A. Sengur, “Effective diagnosis of heart disease through neural networks ensembles,” Expert Systems with Applications, vol. 36, no. 4, pp. 7675–7680, May 2009, doi: 10.1016/j.eswa.2008.09.013.
• [6] A. S. Abdullah and R. R. Rajalaxmi, “A data mining model for predicting the coronary heart disease using random forest classifier,” IJCA Proceedings on International Conference in Recent trends in Computational Methods, Communication and Controls (ICON3C 2012), vol. ICON3C, no. 3, Apr. 2012, Accessed: Jun. 12, 2023. [Online]. Available: https://www.ijcaonline.org/proceedings/icon3c/number3/6020-1021
• [7] Y. E. Shao, C.-D. Hou, and C.-C. Chiu, “Hybrid intelligent modeling schemes for heart disease classification,” Applied Soft Computing, vol. 14, pp. 47–52, Jan. 2014, doi: 10.1016/j.asoc.2013.09.020.
• [8] Ş. Ci̇han, B. Karabulut, G. Arslan, and G. Ci̇han, “Koroner arter hastalığı riskinin veri madenciliği yöntemleri ile incelenmesi,” UMAG, vol. 10, no. 1, Art. no. 1, 2018, doi: 10.29137/umagd.419663.
• [9] Ö. Özmen, A. Khdr, and E. Avci, “Sınıflandırıcıların kalp hastalığı verileri üzerine performans karşılaştırması,” Fırat Üniversitesi Mühendislik Bilimleri Dergisi, vol. 30, no. 3, Art. no. 3, Sep. 2018.
• [10] İ. Ozcan, B. Tasar, A. B. Tatar, and O. Yakut, “Destek vektör makinasi algoritması ile kalp hastalıklarının tahmini,” JCS, vol. 4, no. 2, Art. no. 2, Dec. 2019.
• [11] M. E. Göktaş and M. Yağanoğlu, “Veri bilimi uygulamalarının hastalık teşhisinde kullanılması: Kalp krizi örneği,” JISMAR, vol. 2, no. 2, Art. no. 2, Dec. 2020.
• [12] Ö. Ekrem, O. K. M. Salman, B. Aksoy, and S. A. İnan, “Yapay zekâ yöntemleri kullanılarak kalp hastalığının tespiti,” MBTD, vol. 8, no. 5, Art. no. 5, Dec. 2020, doi: 10.21923/jesd.824703.
• [13] M. Coşar and E. Deni̇z, “Makine öğrenimi algoritmaları kullanarak kalp hastalıklarının tespit edilmesi,” EJOSAT, no. 28, Art. no. 28, Nov. 2021, doi: 10.31590/ejosat.1012986.
• [14] E. A. Potur and N. Ergi̇nel, “Kalp yetmezliği hastalarının sağ kalımlarının sınıflandırma algoritmaları ile tahmin edilmesi,” EJOSAT, no. 24, Art. no. 24, Apr. 2021, doi: 10.31590/ejosat.902357.
• [15] S. Gündoğdu, “Kalp hastalık risk tahmini için Python aracılığıyla sınıflandırıcı algoritmalarının performans değerlendirmesi,” DEUFMD, vol. 23, no. 69, Art. no. 69, Sep. 2021, doi: 10.21205/deufmd.2021236926.
• [16] R. Yilmaz and F. H. Yağin, “A comparatıve study for the predıctıon of heart attack rısk and assocıated factors usıng mlp and rbf neural networks,” JCS, vol. 6, no. 2, Art. no. 2, Dec. 2021, doi: 10.52876/jcs.1001680.
• [17] B. Vatansever, H. Aydin, and A. Çeti̇nkaya, “Genetik algoritma yaklaşımıyla öznitelik seçimi kullanılarak makine öğrenmesi algoritmaları ile kalp hastalığı tahmini,” JSTER, vol. 2, no. 2, Art. no. 2, Dec. 2021, doi: 10.53525/jster.1005934.
• [18] O. K. M. Salman and B. Aksoy, “Rasgele orman ve ikili parçacik sürü zekâsi yöntemiyle kalp yetmezliği hastaliğindaki ölüm riskinin tahminlenmesi,” IJ3DPTDI, vol. 6, no. 3, Art. no. 3, Dec. 2022, doi: 10.46519/ij3dptdi.982670.
• [19] C. Coşkun and F. Kuncan, “Evaluation of performance of classification algorithms in prediction of heart failure disease,” KSU J. Eng. Sci., vol. 25, no. 4, Art. no. 4, Dec. 2022, doi: 10.17780/ksujes.1144570.
• [20] E. Çi̇l and A. Güneş, “Makine öğrenmesi algoritmalarıyla kalp hastalıklarının tespit edilmesine yönelik performans analizi,” ABMYO Dergisi, vol. 17, no. 65, Art. no. 65, Nov. 2022.
• [21] R. Yilmaz and F. H. Yağin, “Early detection of coronary heart disease based on machine learning methods,” Med Records, vol. 4, no. 1, Art. no. 1, Jan. 2022, doi: 10.37990/medr.1011924.
• [22] S. B. Keser and K. Keski̇n, “Kalp yetmezliği hastalarının sağ kalım tahmini: Sınıflandırmaya dayalı makine öğrenmesi algoritmalarının bir uygulaması,” Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol. 23, no. 2, Art. no. 2, May 2023, doi: 10.35414/akufemubid.1033377.
• [23] E. Cevahir, SPSS ile Nicel Veri Analizi Rehberi Egemen Cevahir. İstanbul: Kibele Yayınları, 2020.
• [24] M. B. Wilk and R. Gnanadesikan, “Probability plotting methods for the analysis of data,” Biometrika, vol. 55, no. 1, p. 1, Mar. 1968, doi: 10.2307/2334448.
• [25] U. Çolak, “Makine Öğrenmesi - Veri Ön İşleme,” Medium. Accessed: Sep. 19, 2023. [Online]. Available: https://ufukcolak.medium.com/makine-ogrenmesi-veri-on-isleme-5-58e1ce73c1fb
• [26] U. A. Kimanuka and O. Buyuk, “Turkish speech recognition based on deep neural networks,” SDÜ Fen Bil Enst Der, vol. 22, pp. 319–329, Oct. 2018.
• [27] D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” International Conference for Learning Representations, 2015, doi: 10.48550/arXiv.1412.6980.
• [28] F. Bozkurt, “A study on CNN based transfer learning for recognition of flower species,” EJOSAT, no. 32, Art. no. 32, Dec. 2021, doi: 10.31590/ejosat.1039632.
• [29] Y. Li, Z. Hao, and H. Lei, “Survey of convolutional neural network,” Journal of Computer Applications, vol. 36, no. 9, pp. 2508–2515, 2016.
• [30] Z. Li, W. Yang, S. Peng, and F. Liu, “A survey of convolutional neural networks: Analysis, applications, and prospects,” 2020, doi: 10.48550/ARXIV.2004.02806.