Analysing Chronic Kidney Disease by Using Matlab

Akhilsai P, Pavani V, Dinesh MS and Murali PB

Published on: 2022-02-15


To enhance analysis of the chronic kidney disease prediction using matlab is discusses in this research article. The healthcare data is collected from the healthcare industry, medical laboratories and hospitals. By acquire the required data from the research articles by which data mining technique. In the healthcare data, it comprises of data of any parts in our body and this paper primarily focus on data related to the kidney. The responses gives from the collected input data, which gives analysis of kidney disease.


GFR; Chronic Kidney Disease; Data Mining; Artificial Neural Networks


According to surveys, from the last few decades many advanced features have come in to picture in the field of artificial intelligence. This major advancement has done in medical applications research is limited to medical applications. Among all the medical applications, mostly consider chronic disease for this research. Data mining is the process of extracting hidden information from the large dataset. Data mining is used in several domains such as image mining, text mining, web mining, graph mining, spatial mining and so on. Data mining techniques are used in various applications like fault diagnosis, medical diagnosis, e-mail filtering, face recognition. Data mining techniques such as classification, clustering and association rule and etc. plays a great role in extracting unknown knowledge from the databases [1]. Acquire the required data from the collected data by using data mining techniques. In the healthcare data it comprises of data of any parts in our body but the require data related to the kidney. According to the range of the output, value will predict the which type of disease.In this work predominantly focused on, prediction of four types of kidney diseases Acute Nephritic Syndrome, Chronic Kidney disease (CKD), Acute Renal Failure and Chronic Glomerulonephritis. Kidney diseases are predicted using data mining algorithms like Artificial neural networks (ANN) [2].

Indicator of the CKD

According to the medical treatment of CKD, the Glomerular Filtration Rate (GFR) is the most indicator used to estimate    kidney health function. Which can be computed from the patient’s blood creatinine, age, race, gender, and other factors depending on the used formulas.  However, the commonly used formula is the Modification of Diet in Renal Disease (MDRD) [3]. Generally testing for GFR can be a complicated and lengthy procedure, because of this doctors use a formula to estimate GFR or eGFR. Accurate estimates of the GFR are important for identifying kidney disease, which often has no symptoms until just before the kidney failure.The standard way to estimate the GFR is with a simple blood test that measures your creatinine levels. Creatinine is a waste product from the digestion of dietary protein and the normal breakdown of muscle tissue [4]. GFR=186*(creat)-1.154*(age)-0.203*((ml/min)/173)m2(1) where for a female, the result should be multiplied by a factor of 0.742.Moreover, the classification of CKD defined by the foundation’s Kidney Disease Outcomes Quality Initiative (KDOQI), National Kidney Foundation (NKF).

Matlab Techniques Utilizations in Medical

The ANN, usually simply called neural network (NN), is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks [5], were a bioinspired mechanism of data processing that enables computers to learn technically similar to human-being brain. A neural network consists of an interconnected group of artificial neurons, and it processes information using a connection approach to computation. In most cases, an ANN is an adaptive system that changes its structure based on external (input) or internal information that flows through the network during the learning phase. It is properly the most prestigious and adoptable model in all application models in the field of artificial intelligence. ANN is a mathematical computational method that is used in different areas of science such as approximation of functions, numerical solutions for PDEs and ODEs, speech recognition, videos games, medical diagnosis, and in many other domains. In the literature, there are many different types of neural network models; however, the study is limited to the Back-Propagation Neural Network (BPNN) method with Ridge basis functions [6].  The patient of CKD with COVID-19 infection advise that they was not appropriate clinical treatment discussed by henry [7], albuminuria is a sign of kidney disease and means that patient have to much albumin in urine [8].  With or without albuminuria have not been well-studied estimated glomerular filtration rate (eGFR) 25 to 60 ml per minute per 1.73m2 of body surface area [9-10].

Result and Discussion

Forthcoming GFR values going imply from serum creatinine is measured [11-12] addition to that classification of kidney failure with GFR show in Table.1.

Table 1: Classification of GFR Values.


State of Kidney                                   Disease

GFR Value


Kidney damage with normal or increasing in GFR

GFR >= 90


Kidney damage with mild decrease in GFR

GFR in between 60 - 89


Moderate with decrease in GFR

GFR in between 30 - 59


Severe with decrease with GFR

GFR in between 15 – 29


Kidney failure (go for dialysis)

GFR < 15

Equation (1) with the help of Matlab an detail analysis of GFR as been depicted .As GFR is a measure of how well your kidneys filter blood.Generally for a healthy person the GFR should be greater than 90 and If the GFR of a person is less than 15 then his/her kidney is completely fialure.Cretinine is a waste product  which exists in your body in urine.Everyone has creatinine in their blood but high levels of cretinine in the blood can be a sign that the kidneys are not filtering the blood effectively.From the analysis of GFR vs create graph observe that increase in creatinine leads to the decrease in GFR which indicates the abnormal condition of a person as show in (Figure 1,2 and 3).

Figure 1: Analysis of GFR Vs Create.

Figure 2: Analysis of GFR Vs Days.

Figure 3: Analysis of CI Vs Create.


In this article implemented MATLAB for chronic kidney disease on GFR equation with various parameters. The obtained MATLAB results show that the proposed model can be used to make a precise diagnosis of the CKD. As a future work, we propose to implement the model in smart devices and make it available for public health-care users for early diagnoses of the CKD which leads to better treatment and reduces the out- breaks of this disease.


  1. Rady EHA, Anwar AS. Prediction of kidney disease stages using data mining algorithms. Informatics in Medicine Unlocked.2019; 15: 100-178.
  2. Vijayarani S, Dhayanand S. Kidney disease prediction using SVM and ANN algorithms. International Journal of Computing and Business Research (IJCBR). 2015; 6: 1-12.
  3. Matsushita, Kunihiro. Comparison of risk prediction using the CKD-EPI equation and the MDRD study equation for estimated glomerular filtration rate. Jama 2012; 18: 1941-1951.
  4. Almarashi A, Alghamdi M, Mechai I. A new mathematical model for diagnosing chronic diseases (kidney failure) using ANN. Cogent Mathematics & Statistics.2018; 5: 1-8.
  5. Chiu RK. Intelligent systems developed for the early detection of chronic kidney disease. Advances in Artificial Neural Systems.2013; 2013: 1-7.
  6. Ravindra BV, Sriraam N, Geetha M. Chronic kidney disease detection using back propagation neural network classifier. 2018 International Conference on Communication, Computing and Internet of Things (IC3IoT). 2018;
  7. Henry BM, Lippi G. Chronic kidney disease is associated with severe coronavirus disease 2019 (COVID-19) infection. International urology and nephrology.2020; 52: 1193-1194.
  8. ERACODA Working Group. Chronic kidney disease is a key risk factor for severe COVID-19: a call to action by the ERA-EDTA. Nephrology Dialysis Transplantation.2021; 36: 87-94.
  9. Bhatt DL. Sotagliflozin in patients with diabetes and chronic kidney disease. New England Journal of Medicine.2021; 384: 129-139.
  10. Carlson, Nicholas. Increased vulnerability to Covid?19 in chronic kidney disease. Journal of internal medicine.2021;
  11. Levey AS. A new equation to estimate glomerular filtration rate. Annals of internal medicine. 2009; 150: 604-612.
  12. Stevens LA. Assessing kidney function-measured and estimated glomerular filtration rate. New England Journal of Medicine. 2006; 354: 2473-2483.