Chronic kidney disease (CKD) is a global health problem, and early detection and treatment can prevent or delay the progression to end-stage kidney disease. The model was developed using a multi-layer perceptron (MLP) classifier with a dataset that includes a range of patient attributes such as age, blood pressure, specific gravity, albumin, sugar, red blood cells, and several other factors. The dataset contains 24 attributes and a class label for whether the patient has chronic kidney disease (CKD) or not. The data was preprocessed and reduced to a subset of features that were found to be most relevant for predicting CKD. These features include specific gravity, albumin, red blood cell count, serum creatinine, sugar, diabetes mellitus, hemoglobin, packed cell volume, hypertension, and the classification of CKD or not CKD. The model was trained on this reduced dataset and achieved a maximum accuracy of 96.25%.