Application of Big Data Analytics in Minoxidil Drug Development: A Data-Driven Model for Predicting Efficacy and Side Effect Risks

This study presents a data-driven model using the Gradient Boosting Decision Tree (XGBoost) to predict the efficacy and side effect risks of minoxidil in treating androgenetic alopecia. By analyzing a dataset of 5,000 patient records, the model incorporates patient demographics, clinical indicators, medication information, and genetic features. The XGBoost model significantly outperforms traditional methods like logistic regression and support vector machines in predicting therapeutic outcomes and side effects, as evidenced by superior metrics such as MAE, RMSE, F1-Score, and AUC. The findings suggest that this model can effectively support precision medicine by predicting individualized responses to minoxidil treatment.