Kidney damage can lead to chronic kidney disease (CKD), a condition where the kidneys can’t work properly to keep the body healthy. This can cause problems like nerve damage, low RBC count (anemia), weak bones, poor nutrition, and high blood pressure. This study intends to improve CKD prediction accuracy by using machine learning approaches in order to overcome these problems. This study suggests a process for forecasting CKD status using clinical information, which includes data preprocessing, handling missing values, and selecting specific features responsible for CKD. After that, we used machine learning algorithms like logistic regression, random forest, and decision tree classifiers to classify if a person has CKD or non-CKD. This study shows that machine learning techniques can be used to increase the accuracy of CKD predictions by evaluating model performance using criteria like accuracy (A), precision (P), recall (R), F1 score (F1), and execution time. In this paper, logistic regression outperforms with 94% accuracy.