Table 4.

Referenced literature that considered machine-learning-based kidney disease diagnosis.

Study	Contributions	Algorithm	Dataset	Data Type	Performance Evaluation
[13]	Analysis of Chronic Kidney Disease	NB, DT, and RF	Chronic kidney disease dataset	Tabular	Accuracy—100% (RF)
[53]	Kidney disease detection and segmentation	ANN & kernel KMC	100 collected image data of patients Ultrasound	Image	Accuracy—99.61%
[54]	Classification of Chronic kidney disease	LR, Feedforward NN and Wide DL	Chronic kidney disease dataset	Tabular	Feedforward NN (F1-score—99%, Precision—97%, Recall—99%, and AUC—99%)
[55]	Chronic kidney disease	CNN-SVM	Privately own dataset	Tabular	Accuracy—97.67%, Sensitivity—97.5%, Specificity—97.83%
[56]	Detection and localization of kidneys in patients with autosomal dominant polycystic	CNN	Privately own data	Image	Accuracy—95%