Abstract
BACKGROUND: Effective individualized tools to predict cumulative live birth rates are lacking for patients with ovarian endometriomas undergoing In Vitro Fertilization or Intracytoplasmic Sperm Injection after ultrasound-guided ethanol sclerotherapy. This study aimed to construct and validate a nomogram model for predicting the cumulative live birth rate in this specific population. METHODS: This retrospective study analyzed the clinical data of 194 patients with ovarian endometriosis who underwent ethanol sclerotherapy followed by In Vitro Fertilization or Intracytoplasmic Sperm Injection between January 2020 and December 2024. All patients were randomly divided into training (n = 135) and validation (n = 59) cohorts in a 7:3 ratio. Independent risk factors for the cumulative live birth rate were identified through a comprehensive three-stage screening process that included univariate regression, Least Absolute Shrinkage and Selection Operator regression, and multivariate logistic regression analyses. The nomogram model was constructed using the selected variables, and its discrimination, calibration, and clinical utility were assessed using Receiver Operating Characteristic curves, calibration curves, and Decision Curve Analysis. RESULTS: A total of 194 patients were included, with an overall cumulative live birth rate of 50.0% (97/194). Multivariate regression analysis identified four independent predictors of the cumulative live birth rate: previous live birth history, controlled ovarian hyperstimulation protocol, number of oocytes retrieved, and cyst diameter. The nomogram constructed using these variables exhibited good discriminatory ability in both the training and validation cohorts, with areas under the curve of 0.849 (95% Confidence Interval: 0.782-0.912) and 0.853 (95% Confidence Interval: 0.754-0.952), respectively. Bootstrap validation (500 iterations) confirmed the stability of the model. Calibration was acceptable (Hosmer-Lemeshow test, P>0.05), and decision curve analysis indicated a favorable net benefit across a threshold probability range of 10-50%, demonstrating its clinical utility. CONCLUSIONS: This study developed and validated a parsimonious nomogram model that accurately predicts the cumulative live birth rate in patients with ovarian endometriosis undergoing In Vitro Fertilization/Intracytoplasmic Sperm Injection after ethanol sclerotherapy. Based on four key predictors (previous live birth history, controlled ovarian hyperstimulation protocol, number of oocytes retrieved, and cyst diameter), the model demonstrates excellent and robust predictive performance. It serves as an intuitive and reliable clinical tool to support individualized counseling and shared treatment decision-making.