Debal 

and Sitote Journal of Big Data (2022) 9:109 Journal of Big Data
https://doi.org/10.1186/s40537-022-00657-5

RESEARCH Open Access

Chronic kidney disease prediction using

machine learning techniques
Dibaba Adeba Debal1* and Tilahun Melak Sitote2 

*Correspondence:
[email protected] Abstract 
1
Department of Information Goal three of the UN’s Sustainable Development Goal is good health and well-being
Science, College of Computing, where it clearly emphasized that non-communicable diseases is emerging challenge.
Madda Walabu University, Robe, One of the objectives is to reduce premature mortality from non-communicable dis-
Ethiopia
2
Department of Computer ease by third in 2030. Chronic kidney disease (CKD) is among the significant contribu-
Science and Engineering, tor to morbidity and mortality from non-communicable diseases that can affected
School of Electrical Engineering 10–15% of the global population. Early and accurate detection of the stages of CKD
and Computing, Adama Science
and Technology University, is believed to be vital to minimize impacts of patient’s health complications such
Adama, Ethiopia as hypertension, anemia (low blood count), mineral bone disorder, poor nutritional
health, acid base abnormalities, and neurological complications with timely interven-
tion through appropriate medications. Various researches have been carried out using
machine learning techniques on the detection of CKD at the premature stage. Their
focus was not mainly on the specific stages prediction. In this study, both binary and
multi classification for stage prediction have been carried out. The prediction models
used include Random Forest (RF), Support Vector Machine (SVM) and Decision Tree
(DT). Analysis of variance and recursive feature elimination using cross validation have
been applied for feature selection. Evaluation of the models was done using tenfold
cross-validation. The results from the experiments indicated that RF based on recursive
feature elimination with cross validation has better performance than SVM and DT.
Keywords:  Chronic Kidney Disease (CKD), Machine Learning, Random Forest (RF),
Support Vector Machine (SVM)

Introduction
Chronic kidney disease (CKD) is non-communicable disease that has significantly
contributed to morbidity, mortality and admission rate of patients worldwide [2]. It is
quickly expanding and becoming one of the major causes of death all over the world.
A report from 1990 to 2013 indicated that the global yearly life loss caused by CKD
increased by 90% and it is the 13th leading cause of death in the world [1]. 850 million
people throughout the world are likely to have kidney diseases from different factors [3].
According to the report of world kidney day of 2019, at least 2.4 million people die every
year due to kidney related disease. Currently, it is the 6th fastest-growing cause of death
worldwideCKD is becoming a challenging public health problem with increasing prev-
alence worldwide. Its burden is even higher in low-income countries where detection,

© The Author(s) 2022. Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits
use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original
author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third
party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the mate-
rial. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or
exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://​
creat​iveco​mmons.​org/​licen​ses/​by/4.​0/.
Debal and Sitote Journal of Big Data (2022) 9:109 Page 2 of 19

prevention and treatment remain low [2]. Kidney disease is serious public health prob-
lem in Ethiopia affecting hundreds of thousands of people irrespective of age, sex [4].
The lack of safe water, appropriate diet, and physical activities is believed have contrib-
uted. Additionally, communities living in rural area have limited knowledge about the
CKD. According to WHO report of 2017, the number of deaths in Ethiopia due to kid-
ney disease was 4,875. It is 0.77% of total deaths that has ranked the country 138th in the
world. The age-adjusted death rate is 8.46 per 100,000 of the population and the death
rate increased to 12.70 per 100,000 that has ranked the country 109 in 2018 [3].
National kidney foundation classifies stages of CKD into five based on the abnormal
kidney function and reduced Glomerular Filtration Rate (GFR), which measures a level
of kidney function,. The mildest stage (stage 1 and stage 2) is known with only a few
symptoms and stage 5 is considered as end-stage or kidney failure. The Renal Replace-
ment Therapy (RRT) cost for total kidney failure is very expensive. The treatment is not
also available in most developing countries like Ethiopia. As a result, the management of
kidney failure and its complications is very difficult in developing countries due to short-
age of facilities, physicians, and the high cost to get the treatment [4, 5]. Hence, early
detection of CKD is very essential to minimize the economic burden and maximize the
effectiveness of treatments [6]. Predictive analysis using machine learning techniques
can be helpful through an early detection of CKD for efficient and timely interventions
[7]. In this study, Random Forest (RF), Support Vector Machine (SVM) and Decision
Tree (DT) have been used to detect CKD. Most of previous researches focused on two
classes, which make treatment recommendations difficult because the type of treatment
to be given is based on the severity of CKD.

Related works
Different machine-learning techniques have been used for effective classification of
chronic kidney disease from patients’ data.
Charleonnan et  al. [8] did comparison of the predictive models such as K-nearest
neighbors (KNN), support vector machine (SVM), logistic regression (LR), and decision
tree (DT) on Indians Chronic Kidney Disease (CKD) dataset in order to select best clas-
sifier for predicting chronic kidney disease. They have identified that SVM has the high-
est classification accuracy of 98.3% and highest sensitivity of 0.99.
Salekin and Stankovic [9] did evaluation of classifiers such as K-NN, RF and ANN on
a dataset of 400. Wrapper feature selection were implemented and five features were
selected for model construction in the study. The highest classification accuracy is 98%
by RF and a RMSE of 0.11. S. Tekale et al. [10] worked on “Prediction of Chronic Kidney
Disease Using Machine Learning Algorithm” with a dataset consists of 400 instances and
14 features. They have used decision tree and support vector machine. The dataset has
been preprocessed and the number of features has been reduced from 25 to 14. SVM is
stated as a better model with an accuracy of 96.75%.
Xiao et  al. [11] proposed prediction of  chronic kidney disease progression using
logistic regression, Elastic Net, lasso regression, ridge regression, support vector
machine, random forest, XGBoost, neural network and k-nearest neighbor and com-
pared the models based on their performance. They have used 551 patients’ history
data with proteinuria with 18 features and classified the outcome as mild, moderate,
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 3 of 19

severe. They have concluded that Logistic regression performed better with AUC of
0.873, sensitivity and specificity of 0.83 and 0.82, respectively.
Mohammed and Beshah [13] conducted their research on developing a self-learn-
ing knowledge-based system for diagnosis and treatment of the first three stages of
chronic kidney have been conducted using machine learning. A small number of data
have been used in this research and they have developed prototype which enables the
patient to query KBS to see the delivery of advice. They used decision tree in order to
generate the rules. The overall performance of the prototype has been stated as 91%
accurate.
Priyanka et al. [12] carried out chronic kidney disease prediction through naive bayes.
They have tested using other algorithms such as KNN (K-Nearest Neighbor Algorithm),
SVM (Support Vector Machines), Decision tree, and ANN (Artificial Neural Network)
and they have got Naïve Bayes with better accuracy of 94.6% when compared to other
algorithms.
Almasoud and Ward [13] aimed in their work to test the ability of machine learning
algorithms for the prediction of chronic kidney disease using subset of features. They
used Pearson correlation, ANOVA, and Cramer’s V test to select predictive features.
They have done modeling using LR, SVM, RF, and GB machine learning algorithms.
Finally, they concluded that Gradient Boosting has the highest accuracy with an F-meas-
ure of 99.1.
Yashfi [14] proposed to predict the risk of CKD using machine learning algorithms by
analyzing the data of CKD patients. Random Forest and Artificial Neural Network have
been used. They have extracted 20 out of 25 features and applied RF and ANN. RF has
been identified with the highest accuracy of 97.12%.
Rady and Anwar [15] carried out the comparison of Probabilistic Neural Networks
(PNN), Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Radial Basis
Function (RBF) algorithms to predict kidney disease stages. The researchers conducted
their research on a small size dataset and few numbers of features. The result of this
paper shows that the Probabilistic Neural Networks algorithm gives the highest overall
classification accuracy percentage of 96.7%.
Alsuhibany et al. [16] presented ensemble of deep learning based clinical decision sup-
port systems (EDL-CDSS) for CKD diagnosis in the IoT environment. The presented
technique involves Adaptive Synthetic (ADASYN) technique for outlier detection pro-
cess and employed ensemble of three models, namely, deep belief network (DBN), kernel
extreme learning machine (KELM), and convolutional neural network with gated recur-
rent unit (CNN-GRU).
Quasi-oppositional butterfly optimization algorithm (QOBOA) technique is also
employed in the study for hyperparameter tuning of DBN and CNN-GRU. The research-
ers have concluded that EDL-CDSS method has the capability of proficiently detecting
the presence of CKD in the IoT environment.
Poonia et al. [17] employed Various machine learning algorithms, including k-nearest
neighbors algorithm (KNN), artificial neural networks (ANN), support vector machines
(SVM), naive bayes (NB), and Logistic Regression as well as Re-cursive Feature Elimina-
tion (RFE) and Chi-Square test feature-selection techniques. Publicly available dataset of
healthy and kidney disease patients were used to build and analyze prediction models.
Debal and Sitote Journal of Big Data (2022) 9:109 Page 4 of 19

The study found that a logistic regression-based prediction model with optimal features
chosen using the Chi-Square technique had the highest accuracy of 98.75%.
Vinod [18] carried out the assessment of seven supervised machine learning algo-
rithms namely K-Nearest Neighbor, Decision Tree, Support vector Machine, Random
Forest, Neural Network, Naïve Bayes and Logistic Regression to find the most suitable
model for BCD prediction based on different performance evaluation. Finally, the result
showed that k-NN is the best performer on the BCD dataset with 97% accuracy.
The above reviews indicates that several studies have been conducted on chronic kid-
ney disease prediction using machine-learning techniques. There are various parameters
which play important role in improving model performance like dataset size, quality of
dataset and the time dataset collected. This study focuses on chronic kidney disease pre-
diction using machine learning models based on the dataset with big size and recent
than online available dataset collected from St. Paulo’s Hospital in Ethiopia with five
classes: notckd, mild, moderate, severe, and ESRD and binary classes: ckd and notckd
by applying machine-learning models. Most previously conducted researches focused
on two classes, which make treatment recommendations difficult because the type of
treatment to be given is based on the stages. Table 1 below shows the summary of some
related works.

Table 1  Summary of some related works

No. Author Technique applied Claimed outcome Draw back

1 Salekin and Stankovic K-NN, RF, and NN, Detection F1-score of RF 99.8 Small dataset size with
[9] Wrapper approach and missing values was used;
Embedded approach Severity level prediction
was not included
2 Tekale et al. [10] DT and SVM DT and SVM with an accuracy Dataset size need to
of 91.75 and 96.75 respec- increased, Severity level
tively prediction was not
included. Only to classi-
fiers result compared
3 Priyanka et al. [12] NB, KNN, SVM, DT, and NB, KNN, SVM, DT, and ANN. Small size dataset.
ANN. NB NB accuracy is 94.6% No stages prediction.
Feature extraction was
not carried out and clas-
sification accuracy needs
improvement
4 Yashfi [14] RF and ANN RF and ANN with an accuracy Small size dataset and no
of 97.12% and 94.5% stages prediction
5 Rady and Anwar [15] PNN, MLP, SVM, RBF PNN, MLP, SVM, RBF accuracy Small data size. the
of 96.7, 60.7, 87, and 51.5 algorithms, which is not
respectively appropriate for small
dataset size were used
6 Alsuhibany et al. [16] EDL-CDSS technique, The proposed EDL-CDSS The size of benchmark
ADASYN based outlier method has depicted the dataset is small. IoT
detection and QOBOA other approaches with the and benchmark data
based hyperparameter superior sensy and specy integration is not clearly
tuning of 0.9680 and 0. 9702 explained. The study
compared to ACO, FNC, KELM, focus only on binary
CNN-GRU, DBN, DT, MLP and classification (ckd or
D-ACO not-ckd)
7 Poonia et al. [17] KNN, ANN, SVM, NB KNN, ANN, SVM, Small size dataset and no
and LR with Chi-Square NB, LR accuracy of stages prediction. Accu-
and RFE 66.25%,65%,97.5%,95%,97.5% racy needs improvement
respectively
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 5 of 19

Materials and method
Data source and description
The data source for this study is St. Paulo’s Hospital. It is the second-largest public
hospital in Ethiopia which admits large number of patients with chronic diseases.
There are dialysis treatment and kidney transplant center in the hospital. As it has
been shown in Table 2, the dataset for this study is patients’ records of chronic kidney
disease from patients admitted to the renal ward during 2018 to 2019. Some of them
were obtained from the same patient history data at different times of different stages.
To prepare the dataset and understand features, interviews of domain experts have
been conducted. The dataset contains 1718 instances with 19 features where 12 are
numeric and 7 are nominal. As the detail have been shown in Table 3, the features in
the dataset include Age, Gender, blood pressure, specific gravity, chloride, sodium,
potassium, blood urine nitrogen, serum creatinine, hemoglobin, red blood cell count,
white blood cell count, mean cell volume, platelet count, hypertension, diabetic mel-
litus, anemia and heart disease. When we see multi class distribution, 441 (25.67%)
instances are end-stage renal disease stage or stage five, 399 (23.22%) are at a severe
stage or stage four, 354 (20.61%) are at a moderate stage or stage three, 248 (14.44%)
are at a mild stage or stage two, and 276 (16.07%) have no chronic kidney disease or
normal. The class distribution for binary class is 1442 (83.93%) ckd (stage 1 to 5) and
276 (16.07%) notcckd. The binary-class distribution is imbalanced. Oversampling data
resampling technique have been used to balance the value of the minority class with
the value of the majority class. After employing the resampling technique, the total
size of binary class dataset, become 2888.

Preprocessing
Real world data is often inconsistent which can affect the performances of mod-
els. Preprocessing the data before it is fed into classifiers is vital part of developing

Table 2  Dataset description

Description Values

Data source St. Paul’s

Hospital,
Addis Ababa,
Ethiopia
Period 2018 to 2019
No. of instances 1718
No. of features 19
Class Both binary
and multi
class (5
stages)
End-stage renal disease stage (stage five) 25.67%
Severe stage (stage four) 23.22%
Moderate stage (stage three) 20.61%
Mild stage (stage two) 14.44
Percentage of negative samples 16.07%
Debal and Sitote Journal of Big Data (2022) 9:109 Page 6 of 19

Table 3  Features description

Symbols Features full name Type Class Missing values in %

Age Age Numeric Predictor 0

Gender Gender Nominal Predictor 0
Bp Blood pressure Numeric Predictor 0.058207
Sg Specific gravity Nominal Predictor 0.058207
Chl Chloride Numeric Predictor 0.116414
Sod Sodium Numeric Predictor 0.232829
Pot Potassium Numeric Predictor 0.116414
Bun Blood Urea Nitrogen Numeric Predictor 0.232829
Scr Serum Creatinine Numeric Predictor 0.058207
Hgb Hemoglobin Numeric Predictor 0.232829
Rbcc Red blood cell count Numeric Predictor 0.232829
Wbcc White blood cell count Numeric Predictor 0.232829
Mcv Mean cell volume Numeric Predictor 6.111758
Pltc Platelet count Numeric Predictor 7.275902
Htn Hypertension Nominal Predictor 0
Dm Diabetes Mellitus Nominal Predictor 0
Ane Anemia Nominal Predictor 0
Hd Heart disease Nominal Predictor 0
ckd_status ckd_status Nominal Target 0

Fig. 1  Chronic kidney disease dataset preprocessing steps

machine-learning model. Similarly, the dataset for this study contains missing values
that needs to be handled appropriately. It has to also be in a suitable format for mod-
eling. Hence, pre-processing has been conducted as it has been shown in Fig. 1.
Cleaning Noisy Data: removing outlier and smoothening noisy data is an important
part of preprocessing. Outliers are values that lies away from the range of the rest of
the values. In clinical data, outliers may arise from the natural variance of data. The
potential outliers are the data points that fall above Q3 + 1.5(IQR) and below Q1 − 1.5
(IQR), where Q1 is the first quartile, Q3 is the third quartile, and IQR = Q3 − Q1 [19].
Handling Missing Values: data is not always available (or missed) due to equipment
malfunction, inconsistent with other recorded data and thus deleted, not entered into
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 7 of 19

the database due to misunderstanding, some data may not be considered important at
the time of entry.
Patient data often has missing diagnostic test results that would help to predict the
likelihood of diagnoses or predict treatment’s effectiveness [20]. The missing values have
an impact on the performance of the prediction model. There are several ways of han-
dling missing values including dropping missing values and filling missing values. Some-
times missing values are ignored if they are small percentage i.e., if missing data under
10%. But it is not considered healthy for the model because the missing value can be
an important feature contributing to the model development. Sometimes the missing
values can be also replaced by zero, which will bring no change to the model. To handle
these missing values the mean, an average of the observed features used in this study,
because the missing features are numeric and mean imputation is better for numerical
missing values.
Handling Categorical Data: In this step, data has been transformed into the required
format. The nominal data converted into numerical data of the form 0 and 1. For
instance, ‘Gender’ has the nominal value that can be labeled as 0-for female and 1-for
male. After preprocessing the data then the resultant CSV file comprises all the integer
and float values for different CKD related features.
Normalization: It is important to scale numerical features before fitting to any mod-
els, as scaling is mandatory for some techniques such as nearest neighbors, SVMs, and
deep learning [21]. There are different techniques of scaling and in this study Z-score
normalization (or zero-mean normalization) have been used. The values for a feature are
normalized based on the mean and standard deviation. It is as follows:
x−µ
z= (1)
σ

where z is Z-score, x is feature value, µ is mean value and σ is standard deviation.

Feature selection
Identify subset of relevant predictive features is important for quality result [22]. Feature
selection is the process of selecting most important predictive features to use them as
input for models. It is important preprocessing step to deal with the problem of high
dimensionality. Hence, the main aim of feature selection is to select the subset of fea-
tures that are relevant and independent of each other for training the model [23]. Simi-
larly, feature selection is crucial to develop chronic kidney disease predictive model. This
reduces the dimensionality and complexity of the data and makes the model be faster,
more effective and accurate. Hence, feature selection algorithm have been used to select
relevant features after the construction of the dataset.
Filter, wrappers, or embedded techniques are widely used for feature selection in dif-
ferent clinical datasets including chronic kidney disease. A filter method is a technique
that is independent of a classification algorithm and uses general characteristics of data
for evaluating and selecting relevant features. The filter method works independently of
the learning algorithm to remove irrelevant features and analyses properties of a data-
set to chooses relevant features [24]. It is widely used approach due to its less complex
in nature. With wrapper method, relevant features are selected using the classification
Debal and Sitote Journal of Big Data (2022) 9:109 Page 8 of 19

algorithm. It is better than filter feature selection technique in terms of accuracy. How-
ever, it requires higher processing time. In this study, univariate feature selection method
from filter methods have been selected because it is fast, efficient and scalable. Recursive
feature elimination with cross-validation (RFECV) has been used from wrapper feature
selection method.
Univariate Feature Selection (UFS): This method is popular, simplistic and fastest fea-
ture selection method used in healthcare dataset. It considers each feature separately to
determine the strength of the relationship of the feature with the dependent variable. It
is fast, scalable and independent of classifier. Different options are there for univariate
algorithms such as Pearson correlation, information gain, chi-square, ANOVA (Analysis
of Variance). In this study, feature selection was done using  the ANOVA as shown in
Eq. 2.

MST
F= (2)
MSE

where F is ANOVA coefficient, MST is mean sum of squares of treatment and MSE is

mean sum of squares error.
Recursive Feature Elimination with Cross-Validation (RFECV): An optimization algo-
rithm to develop a trained machine-learning model with relevant and selected features
by repeatedly eliminating irrelevant features. It repetitively creates the model, keeps
aside the worst performing feature at each iteration, and builds the next model with the
remaining features until the features are completed to select best subset of features [25].
It eliminates the redundant and weak feature whose deletion least affects the training
and keeps the independent and strong feature to improve the generalization perfor-
mance of the model [26]. This method uses the iterative procedure for feature ranking
and to find out the features that have been evaluated as most important.  Because this
technique work interacting with a machine learning model, it first builds the model on
the entire set of features and ranked the feature according to its importance.

Machine learning models

The aim of the study was to predict chronic kidney disease using machine-learning tech-
niques. Three machine learning algorithms; Random Forest, Support Vector Machine
and Decision Tree have been used in this study. The algorithms were selected based on
their popularity in chronic kidney disease prediction and their performance of classifica-
tion on previous research works [12, 27–33].
Random Forest: Random Forest is ensemble learning that consists of several collec-
tions of decision trees. It is used for both classification and regression. This model com-
prises of a number of decision trees and outputs the class target that is the highest voting
results of the target output by each tree [28]. Random Forest uses both bagging and ran-
dom feature selection to build the tree and creates an uncorrelated forest of trees. Its
prediction by the group is more accurate than that of any individual tree. After it builds
the forest, test instances are permeated down through each tree and trees make their
respective prediction of class [33]. The Random Forest pseudocode is shown in Fig. 2.
Support vector machine (SVM): Support Vector Machine is one of the promi-
nent and convenient supervised machine-learning algorithm that can be used for
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 9 of 19

Fig. 2  Random forest pseudocode [18]

Fig. 3  SVM pseudocode [18]

classification, learning and prediction. A set of hyperplanes are built to classify all
input in high dimensional data. A discrete hyperplane is created in the signifier space
of the training data and compounds are classified based on the side of the hyperplane
[30]. Hyperplanes are decision boundaries that separate the data points. Support vec-
tors are data points that are closer to the hyperplane and determine the position and
orientation of the hyperplane. SVMs have been mainly proposed to deal with binary
classification, but nowadays many researchers have tried to apply it to multiclass clas-
sification because there are a huge amount of data to be classified into more than
two classes in today’s world. SVM solves multiclass problems through the two most
popular approaches; one-versus-rest and one-vs-one. In this study, one-versus-
rest has been used. For multi classification, we used OVR with the SVM algorithm.
This method separates each class from the rest of the classes in the dataset. Besides,
because Linear SVC is used in this study, one vs rest is an appropriate method with
Linear SVC. The pseudocode of SVM have been shown in Fig. 3.
Decision Tree (DT): It is one of the most popular supervised machine-learning
algorithms that can be used for classification. Decision Tree solves the problem of
machine learning by transforming the data into a tree representation through sorted
feature values. Each node in a decision tree denotes features in an instance to be
classified, and each leaf node represents a class label the instances belong to. This
model uses a tree structure to split the dataset based on the condition as a predictive
model that maps observations about an item to make a decision on the target value of
instances [34]. Decision Tree pseudocode is shown in Fig. 4 and decision making in
binary class of chronic kidney disease have been shown in Fig. 5.
Debal and Sitote Journal of Big Data (2022) 9:109 Page 10 of 19

Fig. 4  Decision tree pseudocode [18]

Fig. 5  Decision making in binary class of chronic kidney disease

Fig. 6  Model building flow diagram

 Debal and Sitote Journal of Big Data (2022) 9:109 Page 11 of 19

Figure 6 shows the flow of model building using three machine-learning algorithms with
tenfold cross validation. The machine learning models were developed for both multiclass
and binary classification. The best performing model was selected as best machine learning
model from the three algorithms for each classification.

Prediction model evaluation

Performance evaluation is the critical step of developing an accurate machine-learning
model. Prediction model shall to be evaluated to ensure that the model fits the dataset and
work well on unseen data. The aim of the performance evaluation is to estimate the gener-
alization accuracy of a model on unseen/out-of-sample data. Cross-Validation (CV) is one
of the performance evaluation methods for evaluating and comparing models by dividing
data into partitions. The original dataset was partitioned into k equal size subsamples called
folds: nine used to train a model and one used to test or validate the model. This process
repeated k times and the average performance will be taken. Tenfold cross-validation have
been used in this study. Different performance evaluation metrics including accuracy, pre-
cision, recall, f1-score, sensitivity, specificity have been computed.

• True positive (TP): are the condition when both actual value and predicted value are
positive.
• True negative (TN): are the condition when both the actual value of the data point and
the predicted are negative.
• False positive (FP): These are the cases when the actual value of the data point was nega-
tive and the predicted is positive.
• False negative (FN): are the cases when the actual value of the data point is positive and
the predicted is negative.

Accuracy
Accuracy implies the ability of the classification algorithm to predict the classes of the data-
set correctly. It is the measure of how close or near the predicted value is to the actual or
theoretical value [35]. Generally, accuracy is the measure of the ratio of correct predictions
over the total number of instances. The equation of accuracy is shown in Eq. 3.

TP + TN
Accuracy = (3)
TP + FP + TN + FN

Precision
Precision measure the true values correctly predicted from the total predicted values in the
actual class. Precision quantifies the ability of the classifiers to not label a negative example
as positive. The equation of precision is shown in Eq. 4.

TP
Precision = (4)
TP + FP

Macro average is used for multiclass classification because it gives equal weight for
each class. The equation of macro average precision is shown in Eq. 5.
Debal and Sitote Journal of Big Data (2022) 9:109 Page 12 of 19

1 |C| TPi
Precision_macro = (5)
|C| i=1 TPi + FPi

Recall
Recall measure the rate of positive values that are correctly classified. Recall answers the
question of what proportion of  actual positives  are correctly classified. The equation of
recall is shown in Eq. 6.

TP
Recall = (6)
TP + FN

Since the macro average is used in order to compute the recall value of the models, macro
average recall is calculated as follows (Eq. 7).

1 |C| TPi
Recall_macro =
i=1 TPi + FNi
(7)
|C|

F‑measure
F-measure is also called F1-score is the harmonic mean between recall and precision. The
equation of F1-score is shown in Eq. 8.

Precision ∗ Recall
F 1score = 2 ∗ (8)
Precision + Recall

The macro average of F1_score is calculated as follows (Eq. 9).

Precision_macro ∗ Recall_macro
F 1score_macro = 2 ∗ (9)
Precision_macro + Recall_macro

Sensitivity
Sensitivity is also called True Positive Rate. Sensitivity is the mean proportion of actual true
positives that are correctly identified [36]. The equation of sensitivity is shown in Eq. 10.

TP
Sensitivity = (10)
TP + FN

Specificity
Specificity is also called True Negative Rate. It is used to measure the fraction of negative
values that are correctly classified. The equation of sensitivity is shown in Eq. 11.

TN
Specificity = (11)
TN + FP
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 13 of 19

Results and discussions
Feature selection
The features selection process using the two methods; UFS and RFECV resulted two dif-
ferent sets of features. The resulted subset of features have been used in the training of
RF, SVM, and DT. The selected features for both five-class and binary-class are different
because recursive feature elimination with cross-validation can automatically eliminate
less predictive features iteratively depending on the model. Table 4 shows the number of
selected features of binary-class and five-class that set the size of the dataset respectively.

Evaluation results
The Experiment has been carried out based on two feature selection methods and three
classifiers for both binary and five-class classification for 18 models. Training and testing
on these models have been executed using tenfold cross-validation. In tenfold cross-val-
idation, the dataset is partitioned randomly into ten equal size sets. Training the models
was then done by using 10–1 folds and test using one remaining fold. The process is
iterative for each fold. The obtained results are presented in binary and five-class classifi-
cation models. Modeling was first carried out for both binary and five class classification
using preprocessed dataset without applying feature selection methods. Then, modeling
has been experimented by applying the two feature selection methods as it has been dis-
cussed in the following sections.

Binary classification models evaluation results

These classification models were built using the two-class dataset that was converted
from the five-class dataset. The target classes are notckd and ckd. The models are trained
and tested using tenfold CV and other performance evaluation metrics of CV. As it has
been discussed previously, modeling was first conducted on the preprocessed dataset
without applying feature selection methods. Then, feature selection techniques have
been implemented to select the most predictive features. Feature selection was imple-
mented using UFS and RFECV. The performance measures of each test for RF, SVM, and
DT models before feature selection and after feature selection method are presented in
Table 5.
An accuracy of 99.8% resulted in the RF with RFECV model with selected 8 features is
the highest. The result of models before applying feature selection is graphically shown
in Fig. 7.

Table 4  Feature selection results

Feature selection methods Machine learning algorithm Selected features (Binary) Selected
features (five-
Class)

RFECV RF 8 9
SVM 9 10
DT 16 7
UFS (ANOVA) RF 14 14
SVM 14 14
DT 14 14
Debal and Sitote Journal of Big Data (2022) 9:109 Page 14 of 19

Table 5  Binary classification without and with feature selection

Models No of features Acc Prec Rec F1 Sen Spec

RF 18 99.7 99.9 99.5 99.7 99.5 99.9

RF with RFECV 8 99.8 99.9 99.7 99.8 99.7 99.9
RF with UFS 14 99.7 99.9 99.5 99.7 99.5 99.9
SVM 18 96.9 99.1 94.7 96.8 94.7 99.1
SVM with RFECV 9 95.5 98.7 92.2 95.3 92.2 98.8
SVM with UFS 14 96.7 99.4 97.7 98.6 97.7 99.4
DT 18 98.5 99.4 97.6 98.5 97.6 99.4
DT with RFECV 16 98.6 99.4 97.7 98.6 97.7 99.4
DT with UFS 14 98.5 99.4 97.6 98.5 97.6 99.4

Fig. 7  Binary class classification without feature selection

Furtherly, we have carried out hyperparameter optimization using grid search using
cross validation on SVM for binary dataset. This has been done without feature selec-
tion. The performance has been significantly improved to 99.83% which is almost the
same with the highest RF with RFECV. Another experiment on the binary classification
is with Extreme Gradient Boosting (XGBoost). It is a powerful machine learning algo-
rithm that can be used to solve classification and regression problems. The performance
is 98.96% which is not better than RF with RFECV’s performance.

Multiclass classification models evaluation results

The multiclass models were similarly built using the preprocessed five-class dataset. The
models are trained and tested using tenfold CV and evaluated with other performance
evaluation metrics. The performance metrics result of each trained model; RF, SVM,
and DT have been presented for without and with feature selection method as shown in
Table 6. Models were first trained and tested with all features without applying feature
selection methods and then we apply the feature selection methods.
Table  6 shows the CV performance metrics results for three classifiers of multiclass
dataset before and after applying feature selection. The accuracy is 79% from RF with
RFECV with selected 9 features. The result of models after applying feature selection
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 15 of 19

Table 6  Multiclass classification results without and with feature selection

Models No. of Acc Prec Rec F1 Sen Spec
features

RF 18 78.3 79.5 77.4 77.3 77.4 94.5

RF with RFECV 9 79.0 79.8 78.1 77.9 78.1 94.7
RF with UFS 14 77.6 78.9 76.6 76.7 76.7 94.3
SVM 18 63.0 60.9 61.5 59.9 61.6 90.6
SVM with RFECV 10 62.2 58.7 60.7 56.5 60.8 90.5
SVM with UFS 14 61.5 59.2 60.5 58.4 60.5 90.2
DT 18 77.5 79.6 76.4 76.2 76.5 94.3
DT with RFECV 7 78.0 80 76.9 76.6 76.9 94.4
DT with UFS 14 77.9 79.8 76.7 76.4 76.7 94.4

100

90

80

70

60

50

40

30

20

10

0
Random Forest SVM Decision Tree
Accuracy Precision Recall F1-Score Sensivity Specificity
Fig. 8  Multiclass classification results after applying RFECV

is graphically shown in Fig.  8. Similarly, we have carried out hyperparameter optimi-

zation using grid search using cross validation on SVM for multiclass dataset. This has
been done without feature selection. The performance has been significantly improved
to 78.78% which is not better than the highest performing model RF with RFECV.
Another experiment on the multiclass classification is with Extreme Gradient Boosting
(XGBoost). It is a powerful machine learning algorithm that can be used to solve classifi-
cation and regression problems. The performance is 82.56% which is better than RF with
RFECV’s performance.

Discussions
Chronic kidney disease is a global health threat and becoming silent killer in Ethiopia
[6]. Many people die or suffer severely by the disease mainly due to lack of awareness
about the disease and inability to detect early. Thus, early prediction of chronic kidney
disease is believed to be helpful to slow the progress of the disease. Machine learning
plays a vital role in early disease identification and prediction. It supports the decision of
medical experts by enabling them to diagnose the disease fast and accurately.
Debal and Sitote Journal of Big Data (2022) 9:109 Page 16 of 19

In this study, chronic kidney disease prediction has been carried out using machine
learning techniques. The datasets consists of 19 features with numerical and nominal
values along with the class to which each instance belongs. The dataset had missing val-
ues and these missing values were handled at the preprocessing step. After preprocess-
ing, we have prepared two datasets for two tasks; binary classification and multiclass
classification that has five-classes. The dataset comprises 1718 instances. The binary
class dataset was created by converting the five-class dataset to two class labels; notckd
and ckd. All classes except notckd converted to ckd in the binary class dataset. After pre-
paring the dataset to binary classification, it has been observed that the class labels were
imbalanced and we applied the data resampling technique to balance the dataset.
Three machine-learning models and two feature selection methods were used. The
model evaluation was done using tenfold cross-validation and other performance
evaluation metrics such as precision, recall, F1-score, sensitivity, and specificity. The
confusion matrix was used to show the correctly and incorrectly classified classes to
evaluate the performance of the model. Initially, we applied machine learning classifiers
without feature selection for both binary class and five classes. The machine learning
models used in this study are Random Forest, Support Vector Machine, and Decision
tree. Then, feature selection techniques were applied along with the models in order to
select predictive. RFECV and UFS were the two feature selection methods applied to
select the relevant features. UFS is the filtering method, it works independently of the
machine learning model and RFECV is the wrapper method that works depending on
the machine-learning algorithm. RFECV is also automatic feature selection method that
can select features without specifying the number of features to be selected. The number
of selected features is different from model to model as it has been shown in the results.
There were features that has been frequently selected in each feature sets, which indi-
cates that they are the most predictive features and have strong predictive relation to the
class. The most frequently selected features using both feature selection methods in all
models are serum creatinine (Scr), blood urine Nitrogen (Bun), Hemoglobin (Hgb), and
Specific Gravity (Sg). Pltc, Rbcc, Wbcc, Mcv, Dm, and Htn are the next most frequently
selected features.
Several related studies have been conducted to predict chronic kidney disease using
machine learning and other techniques globally. However, there were very limited works
in the context of Ethiopia. The focuses of global studies were mainly on binary classifica-
tion. There were very limited attempt on multiclass classification. Additionally, the size
of the datasets used were small which makes them susceptible for overfitting and diffi-
cult for comparison.
Salekin and Stankovic [9] proposed the method of detecting chronic kidney disease
using K-NN, RF and NN, analysed the characteristics of 24 features, and sorted their
predictability. They have used the dataset of 400 instances comprising 250 ckd and 150
notckd. They have used five features for final model construction and they have evalu-
ated the performance of their model using tenfold cross-validation. Compared to the
proposed solution in this study, this work used small size dataset and only focus on
binary classification (ckd and notckd). Even though dataset used in the previous work
and dataset used in proposed study are not the same, the proposed model in this study
has higher performance compared to the previous work.
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 17 of 19

In the study conducted by Almasoud and Ward [13] Logistic regression, support vec-
tor machines, random forest, and gradient boosting algorithms and feature selection
methods such as the ANOVA test, the Pearson’s correlation, and the Cramer’s V test
were implemented to detect chronic kidney disease. A dataset with 400 instances has
been used. Compared to the proposed model performance of binary class classifica-
tion, the performance of the model in this work is inferior. The kidney disease stages
prediction model was developed by Rady and Anwar using PNN, MLP, SVM and RBF
[15]. They evaluated and compared the performance of the models with accuracy. They
reported accuracy accuracy result were 96.7% for PNN, 87% for RBF, 60.7% for SVM
and 51.5% for MLP. They used dataset of 361 instances with 25 features including the
target class. The total data used in this work has been the data of patients with ckd and
then they calculated the eGFR to identify stages of the disease. PNN with an accuracy of
96.7% and RBF with an accuracy of 87% developed by Rady and Anwar [15] shows better
performance than the model with best performance in this study which is RF based on
RFECV with accuracy of 79% even though models in [15] and two models build in this
study are different. However, the SVM model built in this study perform better than the
SVM model built by Rady and Anwar [15]
In this study, proposed models were evaluated using tenfold cross-validation and other
performance evaluation metrics such as precision, recall, f1_scor, sensitivity, and speci-
ficity. Four machine-learning models; RF, SVM, DT and Extreme Gradient Boosting
(XGBoost) have been implemented before applying feature selection. SVM resulted the
highest accuracy of 99.8% for binary. Its accuracy is 78.78% for five classes. RF resulted
accuracy of 99.7% for binary class and accuracy of 78.3% for five-class. XGBoost resulted
accuracy of 98.96% for binary class. The accuracy of XGBoost is 82.56% for five-class
which is the highest. DT resulted accuracy of 98.5% for binary class and accuracy of
77.5% for five-class. Then, the two feature selection methods were applied to the two
datasets. Both SVM and RF with RFECV resulted the highest accuracy for the binary
class. XGBoost has the highest accuracy of 82.56% for five-class. The result is promising
and we believe that it can be deployed to support medical experts to identify the disease
fast and accurate. Thus, SVM, RF with RFECV and XGBoost is recommended in our
study based on its accuracy, f1score, and other performance evaluation for binary class
and five-class classifications.

Conclusion
Early prediction is very crucial for both experts and patients to prevent and slow down
the progress of chronic kidney disease to kidney failure. In this study three machine-
learning models RF, SV, DT, and two feature selection methods RFECV and UFS were
used to build proposed models. The evaluation of models were done using tenfold cross-
validation. First, the four machine learning algorithms were applied to original datasets
with all 19 features. Applying the models on the original dataset, we have got the high-
est accuracy with RF, SVM, and XGBoost. The accuracy was 99.8% for the binary class
and 82.56% for five-class. DT produced lowest performance compared to RF. RF also
produced the highest f1_score values. SVM and RF with RFECV produced the highest
accuracy of 99.8%for binary class. XGBoost has 82.56% accuracy for five-class datasets
which is the highest. Hencewe believe that multi classification work was very important
Debal and Sitote Journal of Big Data (2022) 9:109 Page 18 of 19

to know the stages of the disease and suggest needed treatments for the patients in order
to save their lives.

Future works
This study used a supervised machine-learning algorithm, feature selection methods to
select the best subset features to develop the models. It is better to see the difference
in performance results using unsupervised or deep learning algorithms models. The
proposed model supports the experts to give the fast decision, it is better to make it a
mobile-based system that enables the experts to follow the status of the patients and
help the patients to use the system to know their status.
Acknowledgements
Not applicable.

Author contributions
The development of the basic research questions, identifying the problems and selecting appropriate machine learning
algorithms, data collection, data analysis, interpretation, and critical review of the paper have been done by DA. The
edition of the overall progress of the work was supported and guided by TM. Both authors read and approved the final
manuscript.

Funding
Not applicable.

Availability of data and materials

The data to conduct this research was collected from the patient history data attends their treatment or died during
a period 2018 to 2019 from St. Paulo’s Hospital. There are no restrictions on the availability of data and the authors are
willing to provide the code as well.

Declarations
Ethics approval and consent to participate
Not applicable.

Consent for publication

Not applicable.

Competing interests
The authors declare that they have no competing interests.

Received: 31 January 2022 Accepted: 24 October 2022

References
1. Radhakrishnan J, Mohan S. KI Reports and World Kidney Day. Kidney Int Reports. 2017;2(2):125–6.
2. George C, Mogueo A, Okpechi I, Echouffo-Tcheugui JB, Kengne AP. Chronic kidney disease in low-income to
middle-income countries: The case f increased screening. BMJ Glob Heal. 2017;2(2):1–10.
3. Ethiopia: kidney disease. https://​www.​world​lifee​xpect​ancy.​com/​ethio​pia-​kidney-​disea​se. Accessed 07 Feb 2020.
4. Stanifer JW, et al. The epidemiology of chronic kidney disease in sub-Saharan Africa: A systematic review and meta-
analysis. Lancet Glob Heal. 2014;2(3):e174–81.
5. AbdElhafeez S, Bolignano D, D’Arrigo G, Dounousi E, Tripepi G, Zoccali C. Prevalence and burden of chronic kidney
disease among the general population and high-risk groups in Africa: A systematic review. BMJ Open. 2018;8:1.
6. Molla MD, et al. Assessment of serum electrolytes and kidney function test for screening of chronic kidney disease
among Ethiopian Public Health Institute staff members, Addis Ababa, Ethiopia. BMC Nephrol. 2020;21(1):494.
7. Agrawal A, Agrawal H, Mittal S, Sharma M. Disease Prediction Using Machine Learning. SSRN Electron J.
2018;5:6937–8.
8. Charleonnan A, Fufaung T, Niyomwong T, Chokchueypattanakit W, Suwannawach S, Ninchawee N. Predictive
analytics for chronic kidney disease using machine learning techniques. Manag Innov Technol Int Conf MITiCON.
2016;80–83:2017.
9. Salekin A, Stankovic J. Detection of Chronic Kidney Disease and Selecting Important Predictive Attributes. In: Proc. -
2016 IEEE Int. Conf. Healthc. Informatics, ICHI 2016, pp. 262–270, 2016.
10. Tekale S, Shingavi P, Wandhekar S, Chatorikar A. Prediction of chronic kidney disease using machine learning algo-
rithm. Disease. 2018;7(10):92–6.
11. Xiao J, et al. Comparison and development of machine learning tools in the prediction of chronic kidney disease
progression. J Transl Med. 2019;17(1):1–13.
 Debal and Sitote Journal of Big Data (2022) 9:109 Page 19 of 19

12. Priyanka K, Science BC. Chronic kidney disease prediction based on naive Bayes technique. 2019. p. 1653–9.
13. Almasoud M, Ward TE. Detection of chronic kidney disease using machine learning algorithms with least number of
predictors. Int J Adv Computer. 2019;10(8):89–96.
14. Yashfi SY. Risk Prediction Of Chronic Kidney Disease Using Machine Learning Algorithms. 2020.
15. Rady EA, Anwar AS. Informatics in Medicine Unlocked Prediction of kidney disease stages using data mining algo-
rithms. Informatics Med. 2019;15(2018):100178.
16. Alsuhibany SA, et al. Ensemble of deep learning based clinical decision support system for chronic kidney disease
diagnosis in medical internet of things environment. Comput Intell Neurosci. 2021;3:2021.
17. Poonia RC, et al. Intelligent Diagnostic Prediction and Classification Models for Detection of Kidney Disease. Health-
care. 2022;10:2.
18. Kumar V. Evaluation of computationally intelligent techniques for breast cancer diagnosis. Neural Comput Appl.
2021;33(8):3195–208.
19. Jasim A, Kaky M. Iintelligent systems approach for classification and management of by. 2017.
20. Saar-tsechansky M, ProvostF. Handling Missing Values when Applying Classi … cation Models. vol. 1, 2007.
21. Data Preparation for Statistical Modeling and Machine Learning. https://​www.​featu​reran​king.​com/​tutor​ials/​machi​
ne-​learn​ing-​tutor​ials/​data-​prepa​ration-​for-​machi​ne-​learn​ing/. Accessed 12 Oct 2020.
22. Oliver T. Machine Learning For Absolute Beginners. 2017.
23. ZarPhyu T, Oo NN. Performance comparison of feature selection methods. MATEC Web Conf. 2016;42:2–5.
24. Koshy S. Feature selection for improving multi-label classification using MEKA. Res J. 2017;12(24):14774–82.
25. Vidhya A. Introduction to Feature Selection methods with an example (or how to select the right variables?). https://​
www.​analy​ticsv​idhya.​com/​blog/​2016/​12/​intro​ducti​on-​to-​featu​re-​selec​tion-​metho​ds-​with-​an-​examp​le-​or-​how-​to-​
select-​the-​right-​varia​bles/. Accessed 24 Mar 2020.
26. Misra P, Yadav AS. Improving the classification accuracy using recursive feature elimination with cross-validation. Int
J Emerg Technol. 2020;11(3):659–65.
27. Aqlan F, Markle R, Shamsan A. Data mining for chronic kidney disease prediction. 67th Annu Conf Expo Inst Ind Eng.
2017;2017:1789–94.
28. Subas A, Alickovic E, Kevric J. Diagnosis of chronic kidney disease by using random forest. IFMBE Proc.
2017;62(1):589–94.
29. Kapoor S, Verma R, Panda SN. Detecting kidney disease using Naïve bayes and decision tree in machine learning. Int
J Innov Technol Explor Eng. 2019;9(1):498–501.
30. Vijayarani S, Dhayanand S. Data Mining Classification Algorithms for Kidney Disease Prediction. Int J Cybern Infor-
matics. 2015;4(4):13–25.
31. Drall S, Drall GS, Singh S. Chronic kidney disease prediction using machine learning : a new approach bharat
Bhushan Naib. Learn. 2014;8(278):278–87.
32. KadamVinay R, Soujanya KLS, Singh P. Disease prediction by using deep learning based on patient treatment history.
Int J Recent Technol Eng. 2019;7(6):745–54.
33. Ramya S, Radha N. Diagnosis of Chronic Kidney Disease Using. pp. 812–820, 2016.
34. Osisanwo FY, Akinsola JET, Awodele O, Hinmikaiye JO, Olakanmi O, Akinjobi J. Supervised machine learning algo-
rithms: classification and comparison. Int J Comput Trends Technol. 2017;48(3):128–38.
35. Acharya A. Comparative Study of Machine Learning Algorithms for Heart Disease Prediction 2017.
36. Amirgaliyev Y. Analysis of chronic kidney disease dataset by applying machine learning methods. In: 2018 IEEE 12th
International Conference Application Information Communication Technology, pp. 1–4, 2010.

Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.