The construction of HMME-PDT efficacy prediction model for port-wine stain based on machine learning algorithms

Hematoporphyrin monomethyl ether-photodynamic therapy (HMME-PDT) is a safe and effective treatment for port-wine stain (PWS). Comprehensive methods for predicting HMME-PDT efficacy based on clinical factors are lacking. This study aims to develop and validate two machine learning models to predict the therapeutic effect of HMME-PDT for PWS. We conducted a retrospective study of 131 facial PWS patients treated with single HMME-PDT at the Second Xiangya Hospital from May 2022 to January 2025. The patients were divided into the training cohort and the validation cohort based on the order of their enrollment. Key clinical features were selected using recursive feature elimination (RFE). We developed and validated prediction models with Extreme Gradient Boosting (XGBoost) and Random Forest (RF) algorithms. Model performance was assessed using confusion matrix and evaluation metrics. RFE identified the top predictive factors: dermoscopy vascular pattern, immediate fluorescence intensity (IFI) after HMME-PDT, the facial port-wine stain area and severity index score, and age. In the training cohort, both models demonstrated strong predictive performance, with accuracies, F1 scores, and AUC values exceeding 0.8. The XGBoost model outperformed with an accuracy of 0.8750, F1 score of 0.8750, and AUC of 0.8636. In the validation cohort, XGBoost model achieved an accuracy and F1 score both greater than 0.73, with an AUC value of 0.7672. It had the better comprehensive performance. Our findings suggest these models are promising for predicting HMME-PDT efficacy in PWS. This is the first study to explore IFI after HMME-PDT in efficacy assessment.