Construction and validation analysis of a risk factor and risk prediction model for radiation dermatitis in patients undergoing postoperative radiotherapy for early stage breast cancer

Background: Building a risk prediction model, validating it, and researching the risk variables for radiation dermatitis in patients receiving post-operative radiotherapy for early breast cancer. Materials and Methods: A total of 326 patients with early-stage breast cancer who underwent postoperative radiotherapy in hospital between August 2020 and August 2023 were selected and divided into 198 in the modeling group and 128 in the validation group; and the modeling group was divided into an occurrence group and a non-occurrence group according to whether they had radiation dermatitis. Logistic regression was used to investigate the risk factors for the development of dermatitis, and the predictive effect of the model was tested by the receiver operating characteristic curve (ROC). Results: Combined diabetes, conventional split radiotherapy, compensatory membrane application, and albumin <40g/L were independent risk factors for radiation dermatitis (P < 0.05); the area under the curve (AUC) was 0.821 and 0.908 in the modeling and validation groups, respectively, P < 0.001, with goodness-of-fit test (Hosmer-Leme-show, H-L) validity. Conclusion: Clinically, it is important to consider the risk factors of radiation dermatitis among patients who receive postoperative radiotherapy for early-stage breast cancer. Utilizing a risk prediction model, doctors can identify and evaluate patients' risk levels, aiding in the timely implementation of preventive measures.