Explainable Artificial Intelligence (XAI) makes the model’s predictions clear and easily interpretable to clinicians, maintaining transparency and trust. This work outlines the development and evaluation of an explainable model for predicting chronic kidney disease by applying Shapley Additive Explanations to the XGBoost model classifier in clinical data. Results reached an accuracy of 98.61% and 95.47% with 5-fold cross-validation, precision of 98.64%, recall of 98.61%, and F1-Score of 98.60%, with the most significant features in decreasing order of importance being serum creatinine, blood glucose random, sodium, blood urea, potassium, and blood pressure.