Construction and validation of a Nomogram prediction model for the risk of moderate to severe acute radiation dermatitis in breast cancer

CUI Na; CHEN Ling; ZHANG Xinchun; PU Yingna; ZHAO Bei

doi:10.12102/j.issn.1009-6493.2025.15.006

Abstract：Objective:To analyze the influencing factors of moderate to severe acute radiation dermatitis in breast cancer and construct a risk prediction model.Methods:A total of 1 709 breast cancer patients who received radiotherapy in the department of breast radiotherapy of the Affiliated Tumor Hospital of Xinjiang Medical University from January 2015 to December 2022 were selected as the research subjects.Multivariate Logistic regression was used to analyze the independent influencing factors of moderate to severe acute radiation dermatitis in breast cancer and construct a dynamic Nomogram prediction model.The receiver operating characteristic(ROC)curve and calibration curve were used to evaluate the discrimination and goodness of fit of the model.Results:Moderate to severe acute radiation dermatitis occurred in 21.1%of breast cancer patients who received radiotherapy.Multivariate Logistic regression analysis showed that body mass index(BMI)>24 kg/m²,high expression of the proliferation index,positive regional lymph node metastasis,diabetes mellitus,allergic dermatitis,and albumin≤35 g/L were independent influencing factors for moderate to severe acute radiation dermatitis in breast cancer patients(P<0.05).The area under the receiver operating characteristic(ROC)curve of the Nomogram prediction model for the risk of moderate to severe acute radiation dermatitis in breast cancer was 0.756[95%CI 0.728-0.785],with a sensitivity of 76.7%and a specificity of 64.7%.Conclusions:The Nomogram prediction model for the risk of moderate to severe acute radiation dermatitis in breast cancer could help medical staff accurately identify high-risk patients at an early stage and reduce the severity of acute radiation dermatitis in breast cancer patients.