Chronic kidney disease is a widespread health problem because it has a high death and illness rate and can lead to other health problems. People who have chronic kidney disease often don't pay attention to their illness because it doesn't show any clear signs at first. When people with chronic kidney disease are diagnosed early, they can start treatment right away, which slows the illness's progression. Models based on ML might help doctors reach this goal more quickly and correctly, as they use quick and accurate markers. We have a ML model that uses six distinct strategies at the same time to identify persons with chronic renal disease. These include RF, logistic regression, naive bayes, KNN, SVM, and feed forward neural network. There were many missing values in UCI's ML-oriented library, which included this type of chronic kidney disease data. To fill in the missing numbers, we utilized KNN imputation. One way to do this is to pick a few complete specimens whose findings are the most like the missing information in each incomplete specimen. To figure out how to identify chronic kidney diseases, we need to be able to use six different machine learning methods at the same time to deal with the missing data set. The ratios for training and testing would then be 80/20. Finally, we use standard performance curves to get an idea of how well the six ML methods work and then check our results.