Our objective was to develop predictive models for fibrosis, which is a crucial symptom response in the retinal health, using baseline characteristics and to identify key biomarkers associated with fibrosis progression. We utilized a comprehensive dataset that includes demographic information, ophthalmic exams (such as OCT and fluorescein angiography), and treatment details from the clinical trials. The data preparation involved integrating multiple datasets to create a robust training set. We employed various machine learning techniques, including ensemble methods (XGBoost, Random Forest), Support Vector Machine (SVM), and partial least squares regression, to develop our models. The models' performance was evaluated based on sensitivity, specificity, and area under the ROC curve (AUC). In the work, all results are done in R markdown which integrate the code, comments and result. Besides, data manipulation is fitted with clinical standard to display demographic statistics table. We hope the result from R could be used in clinics and also create a package for other users to run the machine learning methods as a standardized way in the future.