The machine learning and health care combination are sharply related. Machine Learning can play a crucial role in predicting the presence or absence of kidney disease. An effective method for kidney disease prediction is discussed in this work. The proposed system consists of autoencoder combined with a multilayer perceptron for a classification problem. An autoencoder is an artificial neural network that trains a model to extracting useful features. We used kidney disease analysis as a case study for simulating the proposed system and its efficiency is evaluated against the current approaches. An autoencoder is able to integrate into an optimal representation which is then classified by the MLP network to derive the final output. The proposed system clearly gives a better result than the traditional ones. This learning method has a good effect on the classification of disease prediction and guidance for the diagnosis of disease in medical.
Published In : IJCSN Journal Volume 8, Issue 3
Date of Publication : June 2019
Pages : 229-234
Tables : 01
Juby Mary Abraham :
received her B.Tech (CSE) degree from University of Kerala in 2016. She is currently pursuing her Masters in Computer Science & Engineering from KTU. Her research interests are data mining, machine learning and image processing.
Kavitha V K :
is working as Assistant Professor in computer science and engineering Department. She has more than 10 years' experience in teaching. Her research interests focus data mining and machine learning. She has published several papers on data mining.
Dr. Radhakrishnan B :
is working as the Head of CSE department. He has more than 14 years' experience in teaching and has published papers on data mining and image processing. His research interests include image processing, data mining, image mining.
Machine learning, artificial neural network, Autoencoder, Multilayer Perceptron
An effective method for kidney disease prediction is discussed in this paper. In this work, we proposed a framework for chronic kidney disease classification of data using autoencoders and MLP. Chronic kidney disease dataset is taken for training process of the model. This model is compared with several neural network approaches and other state-of art approaches in the literature. From the results it is evident that the proposed model outperforms other model with an accuracy of 96.475% which is quite excellent for the ideal classification model. Based on the experiments and observations it is concluded that the proposed framework for kidney disease prediction can be used as powerful tool for the disease diagnosis process. This model helps in predicting the chronic kidney disease of a patient with better which are important in the medical world. In the future, this system can be improved using DNN based techniques to enrich the input features.
 Dr. S. Vijayarani1, mr.s.dhayanand, "Kidney disease prediction using svm and Ann algorithms", International Journal of Computing and Business Research (IJCBR).  Sujata Drall, Gurdeep Singh Drall, Sugandha Singh, Bharat Bhushan Naib, "Chronic Kidney Disease Prediction Using Machine Learning: A New Approach", International Journal of Management, Technology And Engineering.  Manish Kumar, "Prediction of Chronic Kidney Disease Using Random Forest Machine Learning Algorithm", IJCSMC, Vol. 5, Issue. 2, February 2016.  M. Praveena, N. Bhavana, "Prediction of Chronic Kidney Disease using c4.5 Algorithm", International Journal of Recent Technology and Engineering(IJRTE).  Himanshu Kriplani, Bhumi Patel and Sudipta Roy, "Prediction of Chronic Kidney Diseases using Deep artificial neural network Technique", Researchgate.  Pinar Yildirim, "Chronic Kidney Disease Prediction on Imbalanced Data by Multilayer Perceptron", 2017 IEEE 41st Annual Computer Software and Applications Conference.