Clinically Applicable Machine Learning Approaches to Identify Attributes of Chronic Kidney Disease (CKD) for Use in Low-Cost Diagnostic Screening

Abstract

Objective: Chronic kidney disease (CKD) is a major public health concern worldwide. High costs of late-stage diagnosis and insufficient testing facilities can contribute to high morbidity and mortality rates in CKD patients, particularly in less developed countries. Thus, early diagnosis aided by vital parameter analytics using affordable computer-aided diagnosis could not only reduce diagnosis costs but improve patient management and outcomes. Methods: In this study, we developed machine learning models using selective key pathological categories to identify clinical test attributes that will aid in accurate early diagnosis of CKD. Such an approach will save time and costs for diagnostic screening. We have also evaluated the performance of several classifiers with k-fold cross-validation on optimized datasets derived using these selected clinical test attributes. Results: Our results suggest that the optimized datasets with important attributes perform well in diagnosis of CKD using our proposed machine learning models. Furthermore, we evaluated clinical test attributes based on urine and blood tests along with clinical parameters that have low costs of acquisition. The predictive models with the optimized and pathologically categorized attributes set yielded high levels of CKD diagnosis accuracy with random forest (RF) classifier being the best performing. Conclusions: Our machine learning approach has yielded effective predictive analytics for CKD screening which can be developed as a resource to facilitate improved CKD screening for enhanced and timely treatment plans.

Early Detection and Diagnosis of Chronic Kidney Disease Based on Selected Predominant Features

“…Moreover, the study of Gudeti et al [ 13 ] aimed to diagnose CKD at an early stage, and as a result, they trained SVM, KNN, and LR models, which achieved accuracy rates of 99.25%, 78.75%, and 77.25%, respectively. In the study by Rashed-Al-Mahfuz et al [ 3 ], a reduced dataset was selected based on different clinical tests and feature significance. Afterward, several ML models were built.…”

“…Chronic kidney disease (CKD) is a condition in which the human kidneys are damaged and unable to filter the blood in a proper way [ 1 ]. It is a nontransmissible disease that causes mortality of large numbers worldwide [ 2 , 3 ] and is very expensive to properly detect and diagnose [ 3 ]. CKD is commonly destructive, expensive, onerous, and often risky; therefore, CKD patients often reach its chronic stages, especially in countries with limited resources [ 4 ].…”

A Machine Learning Method with Filter-Based Feature Selection for Improved Prediction of Chronic Kidney Disease

“…Hence, the proposed approach is compared with the following methods: a probabilistic neural network (PNN) [ 66 ], an enhanced sparse autoencoder (SAE) neural network [ 10 ], a naïve Bayes (NB) classifier with feature selection [ 67 ], a feature selection method based on cost-sensitive ensemble and random forest [ 3 ], a linear support vector machine (LSVM) and synthetic minority oversampling technique (SMOTE) [ 11 ], a cost-sensitive random forest [ 68 ], a feature selection method based on recursive feature elimination (RFE) and artificial neural network (ANN) [ 69 ], a correlation-based feature selection (CFS) and ANN [ 69 ]. The other methods include optimal subset regression (OSR) and random forest [ 9 ], an approach to identify the essential CKD features using improved linear discriminant analysis (LDA) [ 13 ], a deep belief network (DBN) with Softmax classifier [ 70 ], a random forest (RF) classifier with feature selection (FS) [ 71 ], a model based on decision tree and the SMOTE technique [ 12 ], a logistic regression (LR) classifier with recursive feature elimination (RFE) technique [ 14 ], and an XGBoost model with a feature selection approach combining the extra tree classifier (ETC), univariate selection (US), and RFE [ 15 ].…”

“…Furthermore, the features selected by the IG technique were similar to current medical practices. For example, the IG technique ranked albumin, hemoglobin, packed cell volume, red blood cell count, and serum creatinine as the most informative features, and numerous studies have identified a strong correlation between these variables and chronic kidney disease [ 71 , 72 , 73 , 74 ].…”

Specific patterns and potential risk factors to predict 3-year risk of death among non-cancer patients with advanced chronic kidney disease by machine learning

“…[20,[25][26][27][28][29] However, these studies mostly focused on CKD prevention or identification. [21,[30][31][32][33] For mortality prediction in ESRD patients, most studies have focused on populations with only kidney transplant therapy or hemodialysis. [34][35][36] Therefore, this study intends to construct a mortality prediction model with AI for pre-ESRD and ESRD patients.…”