Early detection of heart disease can be achieved by high disease prediction and diagnosis efficiency. Machine learning techniques can help the medical expert in decision making for providing the best treatment. In this paper, an autoencoder neural network classifier is developed for the classification of heart disease medical data sets. The autoencoder were trained to properly classify the clinical data. The proposed classifier is tested on heart disease data sets namely Cleveland and Statlog obtained from the UCI repository and also compared with conventional classification techniques namely Support Vector Machine, Random Forest, K-Nearest Neighbour, Naïve Bayes to concerning its outperformance. Experimental results show that the autoencoder neural network clas¬sifier offers much better classification accuracy, precision, recall and f-measure rates when compared with other conventional methods. The proposed method presents itself as an easily accessible and cost-effective alternative to traditional machine learning methods which are used for the diagnosis. In this study, the implementation of the developed model can potentially support in reducing heart disease among patients.

Artificial Neural Networks, Autoencoder, Heart disease, Classification

[1] Centres for Disease Control and Prevention (CDC), Heart disease in the United States, Available http://www.cdc.gov/heartdisease/facts.htm.
[2] Fact sheet: Cardiovascular disease in India, World health federation.
[3] World Health Organization. The World Health Report 2002. Geneva, Switzerland: WHO, 2002.
[4] M.Ciecholewski, “Ischemic heart disease detection using selected machine learning methods”. International Journal of Computer Mathematics, Vol. 90, No.8, pp. 1734–1759, 2013.
[5] E.A. Zanaty, A. Afifi, “Support Vector Machines (SVMs) with universal kernels”. Applied Artificial Intelligence, Vol. 25, pp. 575–589, 2011.
[6] K. Kalaiselvi, K. Sangeetha, S. Mogana, “Efficient disease classifier using data mining techniques: Refinement of random forest termination criteria”, IOSR-JCE, Vol. 14, pp. 104-111, 2013.
[7] A.K. Ghosh, “On optimum choice of k in nearest neighbour classification”, Computational Statistics & Data Analysis, Vol. 50, pp. 3113 – 3123, 2006.
[8] D.Baldassare, E.Grossi, M. Buscema, M. Intraligi, M.Amato, E.Tremoli, L. Pustina, S. Castelnuovo, S. Sanvito, L.Gerosa, S.Sanvito,L.C.Egros, “Recognition of patients with cardiovascular disease by artificial neural networks”, Annals of Medicine Vol. 36 (8), pp. 630-640, 2004.
[9] J.I.Peláez, J.M.Doña, J.F.Fornari, G.Serra, “Ischemia classification via ECG using MLP neural network”, International Journal of Computational Intelligence Systems, Vol. 7(2), pp.344-352, 2014.
[10] Adetiba, E. Iweanya, V.C. Popoola, S. I.Adetiba, J. N.Menon, “Automated detection of heart defects in athletes based on electrocardiography and artificial neural network”, Cogent Engineering, Vol. 4, Issue.1, pp.1-21, 2017.
[11] R. Das, I. Turkoglu, A. Sengur, “An Effective diagnosis of heart disease through neural network ensembles”, Expert Systems with Applications, Vol. 36, No. 4, pp. 7675-7680, 2009.
[12] Z. Arabas Adi, R. Alizadeh Sani, M. Rosha Zamir, H. Moosaei, A.A. Yarifard, “Computer aided decision making for heart disease detection using hybrid neural network-Genetic algorithm”, Computer Methods and Programs in Biomedicine, Vol. 141, pp. 19-26, 2017.
[13] J.E. Guillermo, J. Luis, Castellanos, E. Sanchez, A.Y. Alanis, “Detection of Heart Murmurs Based on Radial Wavelet Neural Network with Kalman Learning”, Neuro Computing, Vol.164, pp. 307-317, 2015.
[14] P.J. Lisboa, “A review of evidence of health benefit from artificial neural networks in medical intervention”. Neural Networks, Vol. 15, No.1, pp. 11–39, 2002.
[15] H.Yan, Y.Jiang, J.Zheng, C.Peng, 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, 2006.
[16] R. Acharya, P. Subbanna Bhat, S.S. Iyengar, A. Rao, S.Dua, “Classification of heart rate data using artificial neural network and fuzzy equivalence relation”, Pattern Recognition, Vol. 36, No. 1, pp. 61-68, 2003.
[17] L.Shi, Z. Zhang, L. Wang, J. Zhang, “The Aide Diagnosis of Cardiac Heart Disease Using a Deoxyribonucleic Acid Based Backpropagation Neural Network” International Journal of Distributed Sensor Networks, Vol. 5, Issue.1, pp. 38, 2009.
[18] P.N.Chatur, A.Ghatol, FIETE, “Thyroid Disease Recognition Using Artificial Neural Network ” IETE Technical Review, Vol. 17, No. 3, Issue.3, pp.143-145, 2000.
[19] B.L. Betechuoh, T. Marwala, T. Tettey, “Autoencoder networks for HIV classification”, Current Science, Vol. 91, No. 11, pp. 1467-1473, 2006.
[20] R. Hata, M.A.H. Akhand, K. Murase, “Multi-valued autoencoders and classification of large-scale multi-class problem”, International Journal of Advanced Computer Science and Applications, Vol. 8, No. 11, pp. 19-26, 2017.
[21] F.M.Alakwaa,Kumar D.Chaudhary, L.X.Garmire, “Deep learning accurately predicts estrogen receptor status in breast cancer metabolomics data” J Proteome Res, Vol. 17(1), pp.337-347, 2017.