To develop and validate a prediction model for uterine fibroid risk based on clinical characteristics and blood biochemical indicators, and to explore its risk factors and clinical application value. This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care (MIMIC-IV3.0) database, including records of female patients admitted between 2008 and 2022. Patient data, including demographic information, vital signs, clinical symptoms, and laboratory test results, were collected. Patients were divided into training and validation groups in a 7:3 ratio. To avoid multicollinearity, the Least Absolute Shrinkage and Selection Operator (LASSO) regression was used to select variables in the training group, and a prediction model for uterine fibroid risk was constructed using logistic regression analysis. The performance and clinical utility of the model were evaluated using the area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). A total of 18,750 patients were included. LASSO regression and logistic regression identified 16 predictors closely associated with uterine fibroid risk. The calibration curve demonstrated good consistency between predicted and observed results, with no significant difference in the Hosmer-Lemeshow test ( P = 1). The AUC of the model was 0.95 (95% CI, 0.95–0.96), with a sensitivity of 0.88, specificity of 0.92, and prediction accuracy of 0.89 (95% CI, 0.88–0.89). In the validation group, the AUC was 0.95 (95% CI, 0.94–0.96), with a sensitivity of 0.88, specificity of 0.93, and prediction accuracy of 0.89 (95% CI, 0.88–0.90). The model exhibited excellent predictive performance and clinical utility. This study developed a uterine fibroid risk prediction model using the MIMIC database. Through rigorous statistical methods, 16 predictors closely associated with uterine fibroid risk were identified, and the reliability and clinical applicability of the model were validated. This model enables individualized risk prediction for patients and provides a powerful tool for early prediction and risk reduction of uterine fibroids.
He et al. (Fri,) studied this question.