Associations of lipid metabolic parameters with cumulative live birth rate in PCOS patients undergoing IVF/ICSI and development of a nomogram-based predictive model.

Background: Polycystic ovary syndrome (PCOS) is a common endocrine disorder affecting reproductive-aged women, many of whom require Methods: This retrospective analysis included 413 PCOS patients under 40 years old who underwent their first IVF/ICSI cycle between January 2022 and May 2024. The cohort was randomly split into a training set (n = 290) and a validation set (n = 123) at a 7:3 ratio. Lasso regression with 10-fold cross-validation was used for variable selection, followed by leave-one-variable-out sensitivity analysis. Multivariate logistic regression was then applied to build the prediction model. Internal validation employed bootstrap resampling with 1,000 iterations. Model performance was assessed by AUC, calibration curves, and decision curve analysis. A nomogram was constructed for clinical application. Result: Multivariate analysis identified high-quality embryo rate (OR = 1.025, 95% CI: 1.010-1.041, Conclusion: Dyslipidemia, primarily elevated TG, is independently associated with lower CLBR in PCOS patients undergoing IVF/ICSI. Our nomogram incorporates TG, apolipoprotein A, BMI, trigger-day estradiol and progesterone, high-quality embryo rate and high-quality blastocyst rate. This tool may serve as a foundation for future external validation and exploratory risk stratification, though clinical application requires prospective multicenter studies.