Abstract
Objective Endometrial lesions is a frequent complication following breast cancer, and current diagnostic tools have limitations. This study aims to develop a machine learning-based nomogram graph prediction model for the early detection of endometrial lesions in patients. The model is intended to provide risk assessment and facilitate personalized treatment strategies for premenopausal breast cancer patients.Method A retrospective study was conducted on 224 patients who underwent diagnostic curettage post-tamoxifen (TAM) therapy between November 2012 and November 2023. These patients exhibited signs of endometrial abnormalities or symptoms such as colporrhagia. Clinical data were collected and analyzed using R software version 4.3.2 to identify factors influencing the occurrence of endometrial lesions and to evaluate their predictive values. Three machine learning methods were employed to develop a risk prediction model, and the performances of these models were compared. The best-performing model was selected to construct a nomogram of endometrial lesions. Internal validation was conducted using the bootstrap method, and the model’s accuracy and fit were assessed using the concordance index (C-index) and calibration curves.Results Independent risk factors for endometrial lesions included ultrasound characteristics, duration of TAM therapy, presence of colporrhagia, and endometrial thickness (P < 0.05). Among the machine learning methods compared, the LASSO regression integrated with a multifactorial logistic regression model demonstrated strong performance, with a concordance index (C-index) of 0.874 and effective calibration (mean absolute error of conformity: 0.014). This model achieved an accuracy of 0.853 and a precision of 0.917, with a training set AUC of 0.874 (95% CI: 0.794–0.831) and a test set AUC of 0.891 (95% CI: 0.777-1.000), closely matching the predicted risk to the actual observed risk.Conclusion The developed prediction model effectively assesses the likelihood of endometrial lesions in premenopausal breast cancer patients. This model offers a theoretical foundation for improving clinical predictions and devising tailored treatment strategies for this patient group.