Chronic Kidney Disease Prediction with Stages and Recommendation of Suitable Diet Plan

Abstract

chronic kidney disease (CKD) is a type of kidney disease in which there is gradual loss of kidney function over a period of months or years. Prediction of this disease is one of the most important problems in medical fields. So automated tool which will use machine learning techniques to determine the patient’s kidney condition that will be helpful to the doctors in prediction of chronic kidney disease and hence better treatment. The proposed system extracts the features which are responsible for CKD, then machine learning process can automate the classification of the chronic kidney disease in different stages according to its severity. The objective is to use machine learning algorithm and suggest suitable diet plan for CKD patient using classification algorithm on medical test records. Diet recommendation for patient will be given according to potassium zone which is calculated using blood potassium level to slow down the progression of CKD.

Introduction

I. INTRODUCTION

The health-care industry is producing copious amounts of data which need to be mined in order to discover hidden information for effective prediction, diagnosis and decision making. Currently, kidney disease has been a crucial problem. It is one of the leading causes of death in India. Chronic kidney disease (CKD), is delineated by the gradual loss of kidney function. Kidneys filter wastes and excess fluids from your blood, which are then excreted in your urine. If this disease gets worse, wastes can accumulate in the blood and can cause difficulties like high blood pressure, anaemia, weakening of bones, poor nutritional health and nerve damage. Also, kidney disease increases the risk of having heart and blood vessel disease.

The harmful outcomes can be avoided and prevented by early detections, according to researchers conducted. Awareness of CKD among patients is gradually increasing, but still low. The Global Burden of Disease (GBD) 2015 ranks chronic kidney disease as the eighth leading cause of death in India. All over the world, the highest count of patient with diabetes is in India with the projection figure of 57.2 million cases in 2025and also the count of patient with hypertension is expected to double from 2000 to 2025, hence these will make India the reservoir of CKD [1]. The burden of CKD management thus falls largely on primary care providers (PCPs). Hence an accurate, convenient, and automated CKD detection method is important for clinical practice Undiagnosed CKD can be identified, predicting the likelihood that patients will develop chronic disease, and present patient-specific prevention interventions with Machine learning techniques. Accurate predictive models can be created by health systems, which lower risks and eventually improve standards.

The data mining techniques of classification, clustering and association helps in extracting knowledge from large amount of data. Machine learning and data mining techniques together have been the prime factors in determining and diagnosis of various critical diseases. Management of diet depends on the current Glomerular Filtration Rate (GFR rate) and the severity of the disease. We will be classifying the disease in five stages- Stage 1, stage 2 and stage 3, Stage 4, Stage 5. Stage 1 is safe and requires a lenient diet plan to be followed. Whereas stage 2, a potential CKD patient will be given a restricted and strict diet. Keeping the balance of minerals, electrolytes, and liquids inside body will be difficult for stage 3 to 5 patient. Therefore, they have to be under proper dietary guidance.

An important diet for a renal improvement and prevent further harm is essential, which also helps in keeping balance of electrolytes and water in the body. Other than stages of severity, many other factors will contribute in shaping the diet. The blood potassium level, urea level, calcium level, phosphorous level and so on. In this study, to identify suitable diet plan for a CKD patient the main focus will be on blood potassium level.

II.  LITERATURE SURVEY

Table 1: Literature Survey

III. PROPOSED WORK

Chronic kidney disease (CKD) has become a global health issue and is an area of concern. It is a condition where kidneys become damaged and cannot filter toxic wastes in the body. Our work predominantly focuses on detecting life threatening diseases like chronic kidney disease (CKD) using Classification algorithms. Proposed system is an automation for chronic kidney disease prediction using classification techniques.

The proposed system extracts the features which are responsible for CKD, then machine learning process can automate the classification of the chronic kidney disease in different stages according to its severity. The objective is to use machine learning algorithm and suggest suitable diet plan for CKD patient using classification algorithm on medical test records. System uses old data from “UCI Repository” and uses tools such as “Visual Studio” and “SQL Server” to develop application. System is a real time application useful for doctors to identify CKD and related stages and recommending the suitable diet for the patients.

A. Parameters List

Table 2: Parameters list

IV. METHODOLOGY

A. Machine Learning

Machine learning is a process of studying a system based on data. Machine learning is a part of data science where we use machine learning algorithms to process data.

B. Supervised Learning Technique

It’s a predictive model used for the tasks where it involves prediction of one value using other values in the data-set. Supervised learning will have predefined labels. It classifies an object based on the parameters to one of the predefined set of labels. We have many algorithms to build model in supervised learning such as KNN, Naive bayes, Decision Tree, ID3, Random Forest, SVM, Regression techniques etc.…. Depending of the requirement, labels, parameters and data-set we select the appropriate algorithm for predictions. Algorithm is used to build a model that makes predictions based on evidence in the presence of uncertainty.

In this project for prediction, we make use to “Bayesian Classifier or KNN algorithm” which is an efficient and works fine for all different sets of parameters. It also generates accurate results.

V. RESULTS & DISCUSSIONS

A. Experiment Results

Here we build a real time application useful for the society. This project build using Microsoft technologies. CKD datasets trained using KNN algorithm and we got very good results. KNN algorithm is programmed in such a way that, it works for dynamic datasets. KNN algorithm logic is written and it’s our own library. We are getting around 99.77% of accurate results and it takes around 234123 milli seconds for prediction.

VI. FUTURE ENHANCEMENT

A. SMS/Email Module – In the proposed system, admin assigns Id and password for doctors and receptionists and is intimated manually, so we can add SMS/Email module as a future enhancement where doctors and receptionists receive an SMS or Email regarding the Id and password.

B. Query Module- we can add the query module as a future enhancement to the application where doctor, receptionist and admin of the application can interact with each other.

VII. ACKNOWLEDGEMENT

It gives us immense pleasure in submitting this paper “Chronic Kidney Disease Prediction with Stages & Recommendation of Suitable Diet Plan”. We would like to thank Prof. Kruthika C G (Guide) for giving timely & valuable guidance throughout this survey process. We would like to express our colossal gratitude to Dr. T S Manjunath, Principal, Vidya Vikas Institute of Engineering and Technology, Mysuru, for his help and inspiration during the tenure of the process. We also thank Dr. Sudarshan R, Professor and Head of Department of Information Science and Engineering, Vidya Vikas Institute of Engineering and Technology, Mysuru, for his support. We also extend our sincere thanks to all the faculty members of Information Science and Engineering Department, Vidya Vikas Institute of Engineering and Technology, Mysuru, for their constant encouragement and backing.

Conclusion

This project is a medical sector application which helps the medical practitioners in predicting the CKD disease based on the CKD parameters. It is automation for CKD disease prediction and it identifies the disease, its types and complications from the clinical database in an efficient and an economically faster manner. It is successfully accomplished by applying the Naïve Bayes algorithm for classification. This classification technique comes under data mining technology. This algorithm takes CKD parameters as input and predicts the disease based on old CKD patients’ data.

References

[1] A. S. Levey, R. Atkins, and J .Coresh, “Chronic kidney disease as a global public health problem: approaches and initiatives - a position statement from Kidney Disease Improving Global Outcomes”, Kidney International, vol. 72 no.3, pp. 247-259, Aug 2007. [2] V Jha, G. Garcia, and K. Iseki, “Chronic kidney disease: global dimension and perspectives”, Lancet, vol. 382 no. 9888, pp. 260-272, Jul 2013. [3] K.R Lakshmi, Y. Nagesh, and M. VeeraKrishna, \"Performance Comparison of Three Data Mining Techniques for Predicting Kidney Dialysis Survivability\", International Journal of Advances in Engineering and Technology, vol.7, no.1, pp. 242-254, March 2014. [4] G. Caocci, R. Baccoli, R. Littera, S. Orrù, C. Carcassi and G. La Nasa, \"Comparison Between an Artificial Neural Network and Logistic Regression in Predicting Long Term Kidney Transplantation Outcome\", Artificial Neural Networks Kenji Suzuki, IntechOpen, DOI: 10.5772/53104, 2013. [5] T. Di Noia, V. C. Ostuni, F. Pesce, G. Binetti, D. Naso, F. P. Schena, and E. Di Sciascio. \"An end stage kidney disease predictor based on an artificial neural networks ensemble\", Expert Systems with Applications, vol. 40, pp. 4438–4445, 2013 [6] A. Kusiak, B. Dixonb, and Sh. Shaha, \"Predicting survival time for kidney dialysis patients: a data mining approach\", Computers in Biology and Medicine, vol. 35, pp. 311–327, 2005 [7] J. Levman, T. Leung, P. Causer, D. Plewes, and A. L. Martel, \"Classification of dynamic contrast-enhanced magnetic resonance breast lesions by support vector machines,\" Medical Imaging, IEEE Transactions on, vol. 27, pp. 688-696, 2008. [8] N. H. Sweilam, A. Tharwat, and N. A. Moniem, \"Support vector machine for diagnosis cancer disease: A comparative study,\" Egyptian Informatics Journal, vol. 11, pp. 81-92, 2010. [9] E. Gumus, N. Kilic, A. Sertbas, and O. N. Ucan, \"Evaluation of face recognition techniques using PCA, wavelets and SVM,\" Expert Systems with Applications, vol. 37, pp. 6404-6408, 2010. [10] V. Vapnik, \"The nature of statistical learning theory\" Springer Science and Business Media, 2013. [11] C.C. Chang and C.J. Lin, \"LIBSVM: a library for support vector machines,\" ACM Transactions on Intelligent Systems and Technology (TIST), vol. 2, pp. 27, 2011. [12] K. Tufan, \"Noninvasive diagnosis of atherosclerosis by using empirical mode decom-position, singular spectral analysis, and support vector machines,\" Biomedical Research, vol. 24, pp. 303-313, 2013. [13] Soundarapandian P. (2015). UCI Machine Learning Repository[https://archive.ics.uci.edu/ml/datasets/chronic_kidney_disease]. Irvine, CA: University of California, School of Information and Computer Science. [14] Sh. Shamiluulu, M.M. Boukar, Z. Yussupova. “Medical Tool for Assisting Patients in Kazakhstan Polyclinics”. Proceedings: 11th IEEE International Conference on Application of Information and Communication Technologies (ICECCO 2017). Abuja, Nigeria pp: 80-84

Copyright

Copyright © 2022 Pooja N K, Preethi G, Sonali S, Varsha M L, Prof. Kruthika C G. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.