Hospital readmission of Diabetes patients is a persistent burden on the healthcare industry. Artificial Intelligence (AI) based Machine Learning (ML) techniques offer the potential to predict readmission rates and related risk features for diabetic patients. However, complex machine learning-based solutions are often not interpretable and, thus, hard to understand for the relative parties. To this end, this study designs and implements an interpretable model to predict readmission rates and identify the risk features of readmission of diabetes patients. The model applies a range of explainable visualization techniques such as the permutation importance plot, partial dependence plot (PDP), SHapley Additive exPlanations (SHAP), and interpretable classifiers on a publicly available dataset from US hospitals. The bagging random forest model shows the best results with 89\% accuracy and 67\% precision. The interpretable visualization techniques reveal the number of inpatient admissions and emergency visits in a year as the two most critical risk features for the readmission rate of diabetic patients.