{"id":60270,"date":"2024-09-30T11:00:18","date_gmt":"2024-09-30T11:00:18","guid":{"rendered":"https:\/\/biomedpharmajournal.org\/?p=60270"},"modified":"2024-10-09T18:25:11","modified_gmt":"2024-10-09T18:25:11","slug":"chronic-kidney-disease-detection-using-machine-learning-from-analysis-to-framework-development","status":"publish","type":"post","link":"https:\/\/biomedpharmajournal.org\/staging\/vol17no3\/chronic-kidney-disease-detection-using-machine-learning-from-analysis-to-framework-development\/","title":{"rendered":"Chronic Kidney Disease Detection Using Machine Learning: From Analysis to Framework Development"},"content":{"rendered":"\n

Introduction<\/strong><\/p>\n\n\n\n

In recent years, the number of patients suffering\nfrom CKD is elevating. CKD is emerging as one of the major cause for\ncausalities worldwide. As per the recent reports, 324 million people are suffering\nfrom CKD across the globe1<\/sup>. The normal functioning of the kidney\nensures the balanced amount of various salts, ions and other electrolytes in\nthe human body. Kidneys filtrates the blood passing through human body and\nremoves the toxins from the blood stream. One of the major disease effecting the\nnormal operation of the kidney is CKD. The epidemiology of this infectious\ndisease <\/p>\n\n\n\n

Fluctuates across sections and inhabitants, with\ninclining prevalence in the past few years. The major risk causing factors for\nCKD are diabetes, hypertension, obesity, smoking, and a family history of\nkidney disease2<\/sup>. As per statistics available through various reports\npublished by World Health Organization (WHO) 10% of the world’s population is\nestimated affected from CKD, with some proportion  requiring renal replacement cure, such as\ndialysis or kidney transplantation, continuing to rise. Moreover, because of\nCKD there is an increased risk of cardiovascular disease, mortality, and\nreduced quality of life3<\/sup>.<\/p>\n\n\n\n

Clinically, the major hurdle in detection of CKD is its asymptomatic nature in the early stages and majorly the symptoms show in the later stages after substantial damage has already occurred. Preliminary diagnosis for evaluating kidney health can be done through laboratory tests, including serum creatinine, estimated glomerular filtration rate (eGFR), and urine analysis4<\/sup>. Majorly these tests are conducted by assessing the kidney functioning over a window of few months which measures the trend in reduction of kidney functioning.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 1: The prediction process through Machine learning model<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Multiple risk factors contribute to the development and progression of CKD. Diabetes mellitus and hypertension are the leading causes of CKD, accounting for a substantial proportion of cases. Other risk factors include obesity, smoking, older age, family history of kidney disease, and certain genetic disorders. The complex interplay between these factors and the underlying pathophysiological mechanisms of CKD presents a multifaceted challenge in understanding, diagnosing, and managing the disease.<\/p>\n\n\n\n

The clinical diagnosis and management of CKD is primarily dependent upon the glomerulus, a filter present inside the kidney. Majorly the diagnosis is governed by the fact that the symptoms related to non-functional glomerulus become pre-dominant after acute loss have been done5<\/sup>. Estimated glomerular filtration rate (eGFR) is one of the major metric which is measured to define the functionality and progression of CKD. As shown in figure 1 with progression in years of incidence of CKD the eGFR value dips with sharp edge on delay in diagnosis. Therefore it is mandatory to develop methodologies and support system to detect the disease at early stages6, 7<\/sup>.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 2: Stages of CKD w.r.t eGFR5<\/sup><\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

This paper aims to provide a comprehensive overview and development of a framework for CKD detection through various machine learning methods, exploring its epidemiology8<\/sup>. By enhancing our understanding of CKD, its risk factors, and its impact on individuals and society, we can develop targeted interventions and policies that alleviate the burden of this silent epidemic. Additionally, ongoing research efforts and advancements in the machine learning based diagnosis field offer hope for improved supportive diagnostics, novel therapies, and preventive measures that will reshape the future of CKD management9<\/sup>.<\/p>\n\n\n\n

Related Work<\/strong><\/p>\n\n\n\n

The enormous\nnumber of applications of Machine learning algorithms nowadays made it possible\nto act as a decision and diagnosis support system for health care sector as\nwell10<\/sup>. A big set of diseases can be predicted with the help of\neffectively trained model thereby making it possible to save the precious lives\nof the patients11<\/sup>. One of the underlying advantages rises from the\nfact that these models (if effectively trained) can detect the disease at early\nstage of incidence where even the clinical pathology tests fails to detect the\nvariation in the normal parameters. While extensively reviewing the literature,\na number of researchers have been found working towards the development of\ncomputer aided diagnostic support systems for CKD detection.<\/p>\n\n\n\n

In12<\/sup>\na development of an integrated model is proposed. Firstly an individual set of\nmachine learning algorithms were used for the diagnosis development from the\nsample dataset. Then the optimally performing classifiers were selected on the\nbasis of correct judgments to form an integrated approach. The output class\nprimarily belongs to ckd or notckd as predictors. After rigorous analysis and\ntesting the final model was develop by integration of Regression based model\nand Tree based model. The accuracy thus obtained after integration is 99.83%.\nTherefore this method may serve as an efficient diagnostic support system in\nreal time applications.<\/p>\n\n\n\n

An approach\nutilizing the principles of data mining and machine learning is presented in13<\/sup>.\nSeveral classifiers were tested on 400 samples containing 24 variables and 1\npredictor. The least performing classifier is found to be Na\u00efve Bayes and the\nbest performing came out to be Random Forest classifier. An overall accuracy of\n99% is obtained using this approach.<\/p>\n\n\n\n

Utilizing\ndifferent models of machine learning and deep learning is presented in14<\/sup>.\nThe researchers tested various models and a deep learning model and found it\nover performing the machine learning models. Feature optimization methodology based\non 3 feature selection algorithms was developed in order to select the most\noptimum features to ensure higher levels of accuracy. Majorly the division of\ntraining and testing data is done as 50%, 50%. Synthetic Minority Oversampling\nTechnique (SMOTE) in hybridization with regression model gives the optimum\nresults.<\/p>\n\n\n\n

A method\ndeveloped based on ensemble learning is proposed in15<\/sup> to predict the\nrisk level associated with CKD. Major researchers have published their methods\nbased upon dataset containing 400 samples. The number of samples for the\nproposed model in [15] are 1 million samples which validates the performance of\nthe proposed model over good figures of training and testing samples. The stage\nof CKD depends upon the value of parameter glomerular filtration rate (GFR).\nThe prediction of creatinine based on regression model is appended to 23\nfeatures to form a set of 24 predictor variables for evaluating risk\/stage of\nCKD.<\/p>\n\n\n\n

The performance\nevaluation of multiple classifiers for early detection of CKD is presented in16<\/sup>.  The performance of classifiers is tuned using\nadjustment of Hyper-parameters thereby constructing ensemble model with ranking\nweight. The accuracy achieved using the mentioned approach is 98.75%.<\/p>\n\n\n\n

A deep learning based\napproach is presented in17<\/sup>. The researchers\u2019 developed model based\nupon selection of most prominent features thereby improving accuracy. Recursive\nFeature Elimination (RFE) method is deployed to select the optimum feature set\nwith respect to class label. The deep learning method gives high range of\naccuracy and can serve as supportive tool for CKD detection by nephrologists.<\/p>\n\n\n\n

Another model\nbased on ensemble method is proposed in18<\/sup>. Random subspace ensemble\nmethod is found to be the most optimally performing classifier as compared to individual\nclassifier. The implementation is done on the dataset available through UCI\nrepository containing 400 samples. The data pre-conditioning is performed\noptimally by preserving the samples rather than deleting the samples for\nmissing values. The accuracy achieved through the proposed model is found to be\n1.00 while other parameters also in the higher ranges.<\/p>\n\n\n\n

Majorly the methodologies presented in the literature relies upon dataset containing clinical parameters. Few of the researchers have worked upon utilizing 2D Ultrasound images as dataset. The prediction of the risk factors associated with CKD depending upon the values of GFR is also presented in the different articles 19-22<\/sup>.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 3: The Proposed model for CKD detection<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Material and methods<\/strong><\/p>\n\n\n\n

The methodology is divided into three parts: Data pre-processing, Model development followed by model performance evaluation through quality metrics as shown in figure 3.<\/p>\n\n\n\n

Dataset and its processing<\/strong><\/p>\n\n\n\n

To carry\nout the research work the dataset available through UCI Machine learning\nrepository is utilized23<\/sup>. The dataset contains 400 instances of CKD\npatients. The total number of attributes (predictors) are 25 wherein 11 belongs\nto numeric set and 14 belongs to nominal set. The target class corresponds to\nbinary classification case containing 2 possible values ckd or non ckd. While\nanalyzing the dataset, few samples containing missing values are witnessed.\nTherefor data pre-processing is an integral step to ensure unbiased prediction.\nIn order to complete the missing values the corresponding value available in\nthe next row for sample is backfilled24<\/sup>. For data split we have\ntested on 2 scenarios like 70:30, 80:20. The ratio selection 80:20 is\nperforming optimally. 320 instances correspond to training and 80 instances\ncorrespond to testing portion of the data as shown in figure 3. A 5 cross\nvalidation methodology is deployed for validation purposes. Clean and\npreprocess the collected data to ensure its quality and compatibility with the\nmachine learning algorithms.<\/p>\n\n\n\n

 Figure 4 provides information about the attributes available in the dataset. In total 24 attributes along with their nominal ranges\/ units are described through Table 1. For handling nominal values as they belongs to different nominal scales a standardized procedure is to be applied to get the values on the same scale. The original value are mapped to standardized scale.<\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 4: Data and its split up<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Model Development<\/strong><\/p>\n\n\n\n

While making choice of an appropriate machine learning algorithm or integration of algorithms to train the kidney disease detection model, a rigorous set of experimentation is required in order to get best performance. The selection of the optimum model depends primarily on the nature of the problem (classification, regression), availability of dataset (size and type) and the computational resources availability25<\/sup>. Machine learning models are extensively being applied in medical diagnosis applications due to their ability to analyze and process complex patterns present in the data and make predictions for unknown cases based on large amounts of data 26, 27<\/sup>. <\/p>\n\n\n\n

From the literature we have studied a ppopular set of algorithms for classification tasks include decision trees, random forests, support vector machines (SVMs), and deep learning models like convolutional neural networks (CNNs) or rrecurrent neural networks (RNNs). The following section discuss the predominantly used classifiers for CKD detection:<\/p>\n\n\n\n

Logistic Regression (LR)<\/strong><\/p>\n\n\n\n

For binary classification applications like the identification of CKD, logistic regression is a common solution. The target variable in the dataset possess 2 values ckd or notckd. Thereby making LR an optimum choice for the problem under consideration. Based on the input feature vector, this algorithm determines the probabilities of class membership with respect to target class variable. The assumption behind logistic regression is that the target variable’s log-odds and features are linearly related.<\/p>\n\n\n\n

Support Vector Machines (SVMs)<\/strong><\/p>\n\n\n\n

The flexible models known as SVMs are capable of handling both linear and non-linear classification tasks. They operate by locating an ideal hyperplane in a high-dimensional feature space that maximally separates the classes. When dealing with non-linear relationships or with tiny datasets, SVMs can be quite useful.<\/p>\n\n\n\n

Table 1: Predictors and target variables present in data<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
\n

Attribute Name<\/strong><\/p>\n<\/td>\n

\n

Type<\/strong><\/p>\n<\/td>\n

\n

Measurement Unit\/Range<\/strong><\/p>\n<\/td>\n

\n

Attribute category<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Patient age (age)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

Years<\/p>\n<\/td>\n

\n

24 PREDICTORS<\/p>\n<\/td>\n<\/tr>\n

\n

Blood Pressure (bp)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

mm\/Hg<\/p>\n<\/td>\n<\/tr>\n

\n

Specific Gravity (sg)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

(1.005,1.010,1.015,1.020,1.025)<\/p>\n<\/td>\n<\/tr>\n

\n

Albumin (al)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

(0,1,2,3,4,5)<\/p>\n<\/td>\n<\/tr>\n

\n

Sugar (su)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

(0,1,2,3,4,5)<\/p>\n<\/td>\n<\/tr>\n

\n

Red Blood Cells (rbc)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

normal,abnormal<\/p>\n<\/td>\n<\/tr>\n

\n

Pus Cell(pc)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

normal,abnormal<\/p>\n<\/td>\n<\/tr>\n

\n

Pus Cell clumps (pcc)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

present,notpresent<\/p>\n<\/td>\n<\/tr>\n

\n

Bacteria (ba)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

present,notpresent<\/p>\n<\/td>\n<\/tr>\n

\n

Blood Glucose Random (bgr)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

mgs\/dl<\/p>\n<\/td>\n<\/tr>\n

\n

Blood Urea (bu)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

mgs\/dl<\/p>\n<\/td>\n<\/tr>\n

\n

Serum Creatinine (sc)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

mgs\/dl<\/p>\n<\/td>\n<\/tr>\n

\n

Sodium (sod)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

mEq\/L<\/p>\n<\/td>\n<\/tr>\n

\n

Potassium (pot)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

mEq\/L<\/p>\n<\/td>\n<\/tr>\n

\n

Hemoglobin (hemo)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

gms<\/p>\n<\/td>\n<\/tr>\n

\n

Packed Cell<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

 <\/td>\n<\/tr>\n
\n

White Blood Cell Count (wc)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

cells\/cumm<\/p>\n<\/td>\n<\/tr>\n

\n

Red Blood Cell Count (rc)<\/p>\n<\/td>\n

\n

Numerical<\/p>\n<\/td>\n

\n

millions\/cmm<\/p>\n<\/td>\n<\/tr>\n

\n

Hypertension (htn)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

yes,no<\/p>\n<\/td>\n<\/tr>\n

\n

Diabetes Mellitus (dm)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

yes,no<\/p>\n<\/td>\n<\/tr>\n

\n

Coronary Artery Disease (cad)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

yes,no<\/p>\n<\/td>\n<\/tr>\n

\n

Appetite (appet)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

good,poor<\/p>\n<\/td>\n<\/tr>\n

\n

Pedal Edema (pe)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

yes,no<\/p>\n<\/td>\n<\/tr>\n

\n

Anemia (ane)<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

yes,no<\/p>\n<\/td>\n<\/tr>\n

\n

Class<\/p>\n<\/td>\n

\n

Nominal<\/p>\n<\/td>\n

\n

ckd, notckd<\/p>\n<\/td>\n

\n

1 Target with two response classes<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Random Forest<\/strong><\/p>\n\n\n\n

An ensemble learning technique called random forests combines various decision trees to produce predictions. They are renowned for their robustness against overfitting and are capable of handling both classification and regression problems. Random forests are appropriate for chronic renal disease identification where several data types may be involved since they can handle a wide range of feature types, including numerical and categorical variables.<\/p>\n\n\n\n

Gradient\nBoosting Models: The high predictive performance of gradient boosting models\nlike Gradient Boosting Machines (GBM), XGBoost, and LightGBM has made them\npopular. These models sequentially create a group of ineffective learners\n(often decision trees), with each new model fixing the flaws of the prior one.\nIt is well known that gradient boosting models may detect intricate connections\nand patterns in data.<\/p>\n\n\n\n

Deep\nLearning Models: Convolutional and recurrent neural networks (CNNs) in\nparticular have demonstrated promising outcomes in a number of medical\napplications. CNNs are excellent at analyzing spatial patterns, which makes\nthem useful for image-based methods of detecting kidney disease, such as\nexamining kidney MRI or ultrasound pictures. For sequential data, such as\ntime-series measurements or text from medical records, RNNs are effective.<\/p>\n\n\n\n

In order to reduce the biases of individual models and enhance overall prediction performance, ensemble models make use of the diversity of numerous models. They are able to manage complex patterns, lessen overfititng, and provide predictions that are more reliable. It is significant to note that compared to individual models, ensemble models may offer more complexity and computing needs, therefore factors like computational resources and model interpretability should be taken into account.<\/p>\n\n\n\n

Experimental setup for Model Testing and Analysis<\/strong><\/p>\n\n\n\n

For the validation and performance evaluation of the proposed model for CKD detection, dataset consisting 400 samples with 150 ckd instances and 250 notckd instances is utilized. The ratio of target to test split is explicitly taken up for experimentation as 70:30 and 80:20 so as to obtain optimum performance through rigorous testing and experimentation.<\/p>\n\n\n\n

Table 2: Performance evaluation scenarios<\/strong><\/p>\n\n\n\n\n\n\n\n
\n

Name<\/p>\n<\/td>\n

\n

Training set instances<\/strong><\/p>\n<\/td>\n

\n

Testing set instances<\/strong><\/p>\n<\/td>\n

\n

Training Vs. testing+ Validation ratio<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Scenario 1(sc1)<\/p>\n

 <\/p>\n<\/td>\n

\n

280<\/p>\n<\/td>\n

\n

120<\/p>\n<\/td>\n

\n

70:30<\/p>\n<\/td>\n<\/tr>\n

\n

Scenario 2 (sc2)<\/p>\n<\/td>\n

\n

320<\/p>\n<\/td>\n

\n

80<\/p>\n<\/td>\n

\n

80:20<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

<\/p>\n\n\n\n

We have evaluated the performance for different models considering both scenarios so as to select optimum train test ratio and select the suitable classifier model for CKD detection. Figure 5 defines the structure of the confusion matrix and the reference terminology referring to presence and absence of disease.<\/p>\n\n\n\n

The metric used for performance evaluation and comparison of various machine learning classifiers is represented through equation 1. Accuracy is a direct measure of performance so we have focused on calculation of accuracy for model selection.<\/p>\n\n\n\n\n\n
\"\"<\/td>\nFigure 5: Confusion Matrix for CKD detection<\/strong>

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

\"\"<\/figure>\n\n\n\n

Table 3 is depicting the values of maximum accuracy obtained with different set of classifiers for two different scenarios as mentioned in table 2. By analyzing this table we can deduce that for this dataset Ensemble (Subspace\/discriminant) is giving best results in all the scenarios developed for testing.<\/p>\n\n\n\n

Table 3: Model performance terms of accuracy<\/strong><\/p>\n\n\n\n\n\n\n\n
\n

Feature vector<\/strong><\/p>\n<\/td>\n

\n

NB<\/strong><\/p>\n<\/td>\n

\n

KNN<\/strong><\/p>\n<\/td>\n

\n

SVM<\/strong><\/p>\n<\/td>\n

\n

Ensemble (Boosted Trees)<\/strong><\/p>\n<\/td>\n

\n

Ensemble (Subspace\/KNN)<\/strong><\/p>\n<\/td>\n

\n

Ensemble (Subspace\/discriminant)<\/strong><\/p>\n<\/td>\n<\/tr>\n

\n

Scenario 1<\/p>\n<\/td>\n

\n

95.1%<\/p>\n<\/td>\n

\n

94.6%<\/p>\n<\/td>\n

\n

95.3%<\/p>\n<\/td>\n

\n

96%<\/p>\n<\/td>\n

\n

96.2%<\/p>\n<\/td>\n

\n

96.7%<\/p>\n<\/td>\n<\/tr>\n

\n

Scenario 2<\/p>\n<\/td>\n

\n

96.4%<\/p>\n<\/td>\n

\n

96.6%<\/p>\n<\/td>\n

\n

96.6%<\/p>\n<\/td>\n

\n

97.2%<\/p>\n<\/td>\n

\n

97.9%<\/p>\n<\/td>\n

\n

98.4%<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

               <\/p>\n\n\n\n\n\n
\"\"<\/td>\n\n

Figure 6: Accuracy comparison for different classifiers<\/strong><\/p>\n

<\/p>\n

Click here to view Figure<\/a><\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n\n\n

Figure 6 presents comparative performance of different classifiers in terms of accuracy value. As evident from the results Ensemble model is giving best performance as the underlying principle behind its operation is majority voting rule. The purpose of the proposed method is to make the system design in efficient manner so the disease detection process through automation is capable of replacing human efforts.<\/p>\n\n\n\n

Conclusion<\/strong><\/p>\n\n\n\n

This work aims to develop significant contribution for designing computer aided support system for nephrologists. The system thus developed aims at providing decision support to the medical practitioners. The prevalence of CKD is one of the major threat to human population as it causes serious health effects. We have tested the performance of base classifiers as well as the ensemble approaches over the same dataset considering two scenarios by varying test train split ratio. From our experimentation we have found the better performance of ensemble methods over individual classifiers. In order to improve classification performance across a variety of domains, including medical diagnosis, the subspace discriminant ensemble approach offers a framework for merging feature subspace selection and ensemble learning. This approach utilizes the characteristics of different classifies and develop an ensemble based approach. It’s important to remember that the specific problem and dataset characteristics can influence the feature subspace selection method, classifier, and combination strategy selected. We have achieved an accuracy value of 98.4% with train vs. test ratio selected as 80:20 and 96.7% with train vs. test ratio of 70:30. Also we have tested different classifiers for 2 different scenarios considering different training and testing division. This clearly indicates the importance of training the models with higher number of samples containing labelled data. In conclusion, ensemble learning techniques are quite successful at detecting chronic kidney disease (CKD). Ensemble models can take advantage of each model’s advantages by integrating the predictions of several different individual models, which boosts overall predictive performance.<\/p>\n\n\n\n

Acknowledgement<\/strong><\/p>\n\n\n\n

None<\/p>\n\n\n\n

Conflict of Interest<\/strong><\/p>\n\n\n\n

There is no conflict of interest to carry out this work.<\/p>\n\n\n\n

Funding Source<\/strong><\/p>\n\n\n\n

There is no funding sources.<\/p>\n\n\n\n

References<\/strong><\/p>\n\n\n\n

  1. Bhaskar, N.; Suchetha, M.; Philip, N.Y. Time Series Classification-Based Correlational Neural Network With Bidirectional LSTM for Automated Detection of Kidney Disease. IEEE Sens. J. 2021, 21, 4811\u20134818.
    CrossRef<\/a><\/li>
  2. Singh, Vijendra, Vijayan K. Asari, and Rajkumar Rajasekaran. “A deep neural network for early detection and prediction of chronic kidney disease.” Diagnostics<\/em> 12, no. 1 (2022): 116.
     CrossRef <\/a><\/li>
  3. Kovesdy CP. Epidemiology of chronic kidney disease: an update 2022. Kidney Int Suppl (2011). 2022 Apr;12(1):7-11. doi: 10.1016\/j.kisu.2021.11.003. Epub 2022 Mar 18. PMID: 35529086; PMCID: PMC9073222.
     CrossRef <\/a><\/li>
  4. Drew, David A., Daniel E. Weiner, and Mark J. Sarnak. “Cognitive impairment in CKD: pathophysiology, management, and prevention.” American Journal of Kidney Diseases<\/em> 74, no. 6 (2019): 782-790.
     CrossRef <\/a><\/li>
  5. Zhang, William R., and Chirag R. Parikh. “Biomarkers of acute and chronic kidney disease.” Annual review of physiology<\/em> 81 (2019): 309-333.
     CrossRef <\/a><\/li>
  6. Ma, Fuzhe, Tao Sun, Lingyun Liu, and Hongyu Jing. “Detection and diagnosis of chronic kidney disease using deep learning-based heterogeneous modified artificial neural network.” Future Generation Computer Systems<\/em> 111 (2020): 17-26.
     CrossRef <\/a><\/li>
  7. Almasoud, Marwa, and Tomas E. Ward. “Detection of chronic kidney disease using machine learning algorithms with least number of predictors.” International Journal of Soft Computing and Its Applications<\/em> 10, no. 8 (2019).
     CrossRef <\/a><\/li>
  8. M. Patricio et al., \u201cUsing resistin, glucose, age and BMI to predict the presence of breast cancer,\u201d BMC CANCER, vol. 18, Jan. 2018.
     CrossRef <\/a><\/li>
  9. R. J. Kate et al., \u201cPrediction and detection models for acute kidney injury in hospitalized older adults,\u201d Bmc. Med. Inform. Decis., vol. 16, Mar. 2016.
    CrossRef <\/a><\/li>
  10. Y. Chen et al., \u201cMachine-learning-based classification of real-time tissue elastography for hepatic fibrosis in patients with chronic hepatitis B,\u201d Comput. Biol. Med., vol. 89, pp. 18-23, Oct. 2017.
     CrossRef <\/a><\/li>
  11. N. Park et al., \u201cPredicting acute kidney injury in cancer patients using heterogeneous and irregular data,\u201d Plos One, vol. 13, no. 7, Jul. 2018. [22] [23] X. Wang et al., \u201cA new effective machine learning framework for sepsis diagnosis,\u201d IEEE Access, vol. 6, pp. 48300-48310, Aug. 2018.
    CrossRef <\/a><\/li>
  12. Qin, Jiongming, Lin Chen, Yuhua Liu, Chuanjun Liu, Changhao Feng, and Bin Chen. “A machine learning methodology for diagnosing chronic kidney disease.” IEEE Access 8 (2019): 20991-21002.
     CrossRef <\/a><\/li>
  13. Emon, Minhaz Uddin, Rakibul Islam, Maria Sultana Keya, and Raihana Zannat. “Performance analysis of chronic kidney disease through machine learning approaches.” In 2021 6th International Conference on Inventive Computation Technologies (ICICT)<\/em>, pp. 713-719. IEEE, 2021.
     CrossRef <\/a><\/li>
  14. Chittora, Pankaj, Sandeep Chaurasia, Prasun Chakrabarti, Gaurav Kumawat, Tulika Chakrabarti, Zbigniew Leonowicz, Micha\u0142 Jasi\u0144ski et al. “Prediction of chronic kidney disease-a machine learning perspective.” IEEE Access<\/em> 9 (2021): 17312-17334.
     CrossRef <\/a><\/li>
  15. Wang, Weilun, Goutam Chakraborty, and Basabi Chakraborty. “Predicting the risk of chronic kidney disease (ckd) using machine learning algorithm.” Applied Sciences<\/em> 11, no. 1 (2020): 202.
     CrossRef <\/a><\/li>
  16. Srivastava, Swapnita, Rajesh Kumar Yadav, Vipul Narayan, and Pawan Kumar Mall. “An Ensemble Learning Approach For Chronic Kidney Disease Classification.” Journal of Pharmaceutical Negative Results<\/em> (2022): 2401-2409.<\/li>
  17. Singh, Vijendra, Vijayan K. Asari, and Rajkumar Rajasekaran. 2022. “A Deep Neural Network for Early Detection and Prediction of Chronic Kidney Disease” Diagnostics<\/em> 12, no. 1: 116. https:\/\/doi.org\/ 10.3390\/diagnostics12010116
     CrossRef <\/a><\/li>
  18. Jongbo, Olayinka Ayodele, Adebayo Olusola Adetunmbi, Roseline Bosede Ogunrinde, and Bukola Badeji-Ajisafe. “Development of an ensemble approach to chronic kidney disease diagnosis.” Scientific African<\/em> 8 (2020): e00456.
     CrossRef <\/a><\/li>
  19. Revathy, S., B. Bharathi, P. Jeyanthi, and M. Ramesh. “Chronic kidney disease prediction using machine learning models.” International Journal of Engineering and Advanced Technology<\/em> 9, no. 1 (2019): 6364-6367.
     CrossRef <\/a><\/li>
  20. Xiao, Jing, Ruifeng Ding, Xiulin Xu, Haochen Guan, Xinhui Feng, Tao Sun, Sibo Zhu, and Zhibin Ye. “Comparison and development of machine learning tools in the prediction of chronic kidney disease progression.” Journal of translational medicine<\/em> 17, no. 1 (2019): 1-13.
     CrossRef <\/a><\/li>
  21. Kriplani, Himanshu, Bhumi Patel, and Sudipta Roy. “Prediction of chronic kidney diseases using deep artificial neural network technique.” In Computer aided intervention and diagnostics in clinical and medical images<\/em>, pp. 179-187. Springer International Publishing, 2019.
     CrossRef <\/a><\/li>
  22. Jena, Lambodar, Bichitrananda Patra, Soumen Nayak, Sushruta Mishra, and Sushreeta Tripathy. “Risk prediction of kidney disease using machine learning strategies.” In Intelligent and Cloud Computing: Proceedings of ICICC 2019, Volume 2<\/em>, pp. 485-494. Springer Singapore, 2021.
     CrossRef <\/a><\/li>
  23. UCI machine learning repository. (2015):Chronic kidney disease dataset. Accessed February 2023, fromhttp:\/\/archive.ics.uci.edu\/ ml\/datasets\/Chronic_Kidney_disease<\/li>
  24. Jongbo, Olayinka Ayodele, Adebayo Olusola Adetunmbi, Roseline Bosede Ogunrinde, and Bukola Badeji-Ajisafe. “Development of an ensemble approach to chronic kidney disease diagnosis.” Scientific African<\/em> 8 (2020): e00456.
     CrossRef <\/a><\/li>
  25. Sharma, Vivek Kumar, Thakur Gurjeet Singh, Nikhil Garg, Sonia Dhiman, Saurabh Gupta, Md Habibur Rahman, Agnieszka Najda et al. “Dysbiosis and Alzheimer\u2019s disease: a role for chronic stress?.” Biomolecules<\/em> 11, no. 05 (2021): 678.
     CrossRef <\/a><\/li>
  26. Kaushal, Chetna, Shiveta Bhat, Deepika Koundal, and Anshu Singla. “Recent trends in computer assisted diagnosis (CAD) system for breast cancer diagnosis using histopathological images.” Irbm<\/em> 40, no. 4 (2019): 211-227.
     CrossRef <\/a><\/li>
  27. Shukla, Prashant Kumar, Jasminder Kaur Sandhu, AnamikaAhirwar, DeepikaGhai, PritiMaheshwary, and Piyush Kumar Shukla. “Multiobjective genetic algorithm and convolutional neural network based COVID-19 identification in chest X-ray images.” Mathematical Problems in Engineering 2021 (2021): 1-9.
     CrossRef <\/a><\/li><\/ol>\n","protected":false},"excerpt":{"rendered":"

    Introduction In recent years, the number of patients suffering from […]<\/p>\n","protected":false},"author":15,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[117],"tags":[],"class_list":["post-60270","post","type-post","status-publish","format-standard","hentry","category-vol17no3"],"_links":{"self":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/60270","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/users\/15"}],"replies":[{"embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/comments?post=60270"}],"version-history":[{"count":5,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/60270\/revisions"}],"predecessor-version":[{"id":61692,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/posts\/60270\/revisions\/61692"}],"wp:attachment":[{"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/media?parent=60270"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/categories?post=60270"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/biomedpharmajournal.org\/staging\/wp-json\/wp\/v2\/tags?post=60270"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}