A comparative assessment of artificial intelligence models used for early prediction and evaluation of chronic kidney disease

ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application

“… Authors Split ratio Model name Accuracy M.A. Islam et al (2023) 8 70:30 XgBoost 98.3 % R. Sawhney et al (2023) 9 70:30 ANN 100% Alsekait D.M. et al (2023) 6 80:20 DL with SVM 99.69 Arif M.S.…”

“…R. Sawhney et al (2023) 9 developed AI models to predict and assess CKD, using a dataset with 400 cases and 24 features, both categorical and numerical. They utilized a Multilayer Perceptron (MLP) with backpropagation, integrating two feature extraction and three feature selection techniques to improve efficiency.…”

“…Lack of time complexity analysis hinders resource planning, scalability assessment, and real-time suitability. R. Sawhney et al (2023) 9 1. Missing value handling and data scaling techniques were not applied, potentially impacting data quality and model performance.…”

Application of visual transformer in renal image analysis

“…The main clinical applications of renal ultrasonography include ruling out reversible causes of acute kidney injury, such as urinary tract obstruction, or identifying irreversible CKD to rule out unnecessary tests, such as renal biopsy [ 93 ]. Traditional methods of assessing kidney injury have relied on metrics such as kidney length, volume, cortical thickness, and echogenicity [ 94 ]. However, in recent years, advances in deep learning and computer vision have enabled machine learning and artificial intelligence techniques to more accurately and objectively assess kidney images, providing more comprehensive information to diagnose kidney injury and treatment decisions.…”

Chronic Kidney Disease Prediction

“…In Research Paper [9], a multi-layer perceptron classifier is proposed to diagnose chronic kidney disease (CKD) using UCI dataset. They implemented a Deep Neural Network [14] model that achieves 100% accuracy.…”