Early Prediction of Chronic Kidney Disease: A Comprehensive Performance Analysis of Deep Learning Models

Abstract

Chronic kidney disease (CKD) is one of the most life-threatening disorders. To improve survivability, early discovery and good management are encouraged. In this paper, CKD was diagnosed using multiple optimized neural networks against traditional neural networks on the UCI machine learning dataset, to identify the most efficient model for the task. The study works on the binary classification of CKD from 24 attributes. For classification, optimized CNN (OCNN), ANN (OANN), and LSTM (OLSTM) models were used as well as traditional CNN, ANN, and LSTM models. With various performance matrixes, error measures, loss values, AUC values, and compilation time, the implemented models are compared to identify the most competent model for the classification of CKD. It is observed that, overall, the optimized models have better performance compared to the traditional models. The highest validation accuracy among the tradition models were achieved from CNN with 92.71%, whereas OCNN, OANN, and OLSTM have higher accuracies of 98.75%, 96.25%, and 98.5%, respectively. Additionally, OCNN has the highest AUC score of 0.99 and the lowest compilation time for classification with 0.00447 s, making it the most efficient model for the diagnosis of CKD.

Improved Survival Analyses Based on Characterized Time-Dependent Covariates to Predict Individual Chronic Kidney Disease Progression

“…A previous study also showed that the performance of RSF (C-index: 0.965) is significantly better than conventional Cox PHM (C-index: 0.766) for 378 patients with kidney transplantation, with RSF particularly useful for intuitive variable selection [ 24 ]. Recently, Mondol achieved high accuracy in early CKD prediction using convolutional neural network, ANN, and long short-term memory models [ 25 ]. In our recent study, high performance was obtained for predicting CKD progression using random forest methods, with C-indexes of 0.96 within 5 years in the early stage and 0.97 within 1 year in the advanced stage [ 14 ].…”

“…In our recent study, high performance was obtained for predicting CKD progression using random forest methods, with C-indexes of 0.96 within 5 years in the early stage and 0.97 within 1 year in the advanced stage [ 14 ]. Although the models proposed by previous studies show high performance, the quality and accuracy of the estimates may vary over time [ 24 , 25 ]. The use of time-independent covariates for individual risk variables often leads to a higher accuracy rate and overestimation percentage.…”

“…In addition, several risk prediction models have been proposed for CKD applications [ 14 , 19 , 20 , 21 , 22 ]. The published models applied to renal diseases include the Cox proportional hazard model (Cox PHM) [ 19 , 23 ], random survival forest (RSF) [ 24 ], and artificial neural network (ANN) models [ 22 , 25 ]. Cox PHM is the most widely used method to predict the risk factors of clinical diseases in cohort studies.…”

A Comparative Analysis of Machine Learning and Deep Learning Approaches for Prediction of Chronic Kidney Disease Progression

“…It has become increasingly common for people to experience kidney failure, a chronic condition that can take a long time to diagnose [16]. The kidney plays an essential role in the body by filtering waste and excess fluids, and when it is damaged, it cannot effectively clean the blood, which can cause further health issues [17]. In addition to blood tests, imaging tests like ultrasounds, CT scans, and MRIs can detect structural abnormalities in the kidneys such as cysts, tumors, and obstructions [16].…”

Chronic Kidney Disease Prediction

“…In paper [7], they proposed the deep learning algorithms CNN, ANN [16], and LSTM as three optimised versions as well as traditional CNN[17], ANN, and LSTM models to predict CKD at the primary stage. They achieved accuracies of optimized CNN, ANN and LSTM are 98.75%, 96.25%, and 98.5%, respectively where as the achieved accuracies of CNN, ANN and LSTM are 92.71%, 90.43%, and 88.51% respectively.…”