The study developed and validated a machine learning model to predict the risk of unplanned readmission within 1 year in patients with ulcerative colitis (UC), a chronic inflammatory bowel disease with recurrent flare-ups. They used a retrospective cohort of 324 patients for training and a prospective cohort of 137 patients for external validation, with input data such as demographics, medical history, medications, symptoms, laboratory and endoscopic findings. Recursive function elimination (RFE) selected five key predictors: C-reactive protein, erythrocyte sedimentation rate, red blood cell count, increased frequency of bowel movements, and platelet count. All eight machine learning models achieved AUC above 0.75 in the training cohort. The best random forest (RF) model had an AUC of 0.936 in training, 0.815 in internal validation, and 0.813 in external validation. Based on the RF model, an online platform was created to estimate the risk of readmission for personalized care of patients with UC.