Machine Learning Based Classification of Chronic Kidney Disease Using CT Scan Images

CT-Scan imaging has been widely used in kidney diagnosis to estimate kidney size, shape, and position, provide information about kidney function, and help diagnose structural abnormalities like cysts, stones, and infection. However, the use of CT-Scan in kidney diagnosis is operator-dependent. The images may be interpreted differently depending on operators’ skills and experiences, variations in human perceptions of the images, and differences in features used in diagnosis. Chronic kidney disease diagnosis may be improved by implementing automated techniques and computer-aided diagnosis systems, but these have not been widely explored. Therefore, this study proposed that chronic kidney disease has been acquired using the Random Forest classifier with 96.33% accuracy among different Machine Learning classifiers. Overall, this study has shown promising results. Implementing these proposed algorithms into current chronic kidney disease diagnosis techniques may help improve current diagnosis accuracy while reducing human intervention and operator dependency.