To investigate the determinants affecting live birth outcomes in fresh embryo transfer among polycystic ovary syndrome (PCOS) patients using various machine learning (ML) algorithms and to construct predictive models, offering novel insights for enhancing live birth rates in this specific group. A sum of 1,062 fresh embryo transfer cycles involving PCOS patients were analyzed, with 466 resulting in live births. The dataset was split randomly into training and testing subsets at a 7:3 ratio. Least absolute shrinkage and selection operator and recursive feature elimination methods were utilized for feature selection within the training data. A grid search strategy identified the optimal parameters for seven ML models: decision tree (DT), K-nearest neighbors (KNN), light gradient boosting machine (LightGBM), naive Bayes model(NBM), random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGBoost). The evaluation of model effectiveness incorporated diverse metrics, encompassing area under the curve (AUC), accuracy, positive predictive value, negative predictive value, F1 score, and Brier score. Calibration curves and decision curve analysis were employed to ascertain the optimal model. Furthermore, Shapley additive explanations were applied to elucidate the importance of predictor variables in the top-performing model. The AUC values of DT, KNN, LightGBM, NBM, RF, SVM and XGBoost models in the training set were 0.813, 1.000, 0.724, 0.791, 1.000, 0.819 and 0.853, respectively. Corresponding values in the testing set were 0.773, 0.719, 0.705, 0.764, 0.794, 0.806 and 0.822. XGBoost emerged as the most effective ML model. SHAP analysis revealed that variables encompassing embryo transfer count, embryo type, maternal age, infertility duration, body mass index, serum testosterone (T) levels, and progesterone (P) levels on the day of human chorionic gonadotropin administration were pivotal predictors of live birth outcomes in individuals with PCOS receiving fresh embryo transfer. This study developed a live birth prediction model tailored for PCOS fresh embryo transfer cycles, leveraging ML algorithms to compare the efficacy of multiple models. The XGBoost model demonstrated superior predictive capacity, enabling prompt and precise identification of critical risk factors influencing live birth outcomes in PCOS patients. These findings offer actionable insights for clinical intervention, guiding strategies to improve pregnancy outcomes in this population. Not applicable.

Increasing evidence suggests that mitophagy is crucially involved in the progression of polycystic ovary syndrome (PCOS). Exploration of PCOS-specific biomarkers related to mitophagy is expected to provide critical insights into disease pathogenesis. In this study, we employed bioinformatic analyses and machine learning algorithms to determine novel biomarkers for PCOS that may be tied with mitophagy. A grand total of 12 differential expressed mitophagy-related genes (DE‐MRGs) associated with PCOS were identified. TOMM5 and MAP1LC3A among the 12 DE‐MRGs were recognized as potential marker genes by LASSO, RF and SVM‐RFE algorithms. The area under the ROC curve (AUROC) of MAP1LC3A were all greater than 0.8 both in the training set and validation sets. The CIBERSORT analysis indicated a potential association between alterations in the immune microenvironment of PCOS individuals and MAP1LC3A expression. In addition, we found that MAP1LC3A was positively related to the testosterone levels of PCOS patients. Overall, MAP1LC3A was identified as optimal PCOS-specific biomarkers related to mitophagy. Our findings created a diagnostic strength and offered a perspective for investigating the mitophagy process in PCOS.

Background: Related studies have shown that it is safe for cancer patients to undergo assisted reproduction. However, studies on whether a history of cancer affects long-term reproductive outcomes in women who undergo assisted reproductive technology (ART) are scarce. In this study, we evaluated the long-term reproductive outcomes of patients with malignant tumors undergoing ART treatment and explored the impact of malignancy history on ART outcomes.Methods: This retrospective study analyzed the clinical outcomes of patients with malignant tumors undergoing their first in vitro fertilization/intracytoplasmic sperm injection (IVF/ICSI) cycles compared with those of age-matched healthy infertile women at Fujian Maternity and Child Health Hospital between January 2003 and October 2020. We evaluated ovarian stimulation outcome, the pregnancy rate, the live birth rate, the risk of adverse obstetric outcomes and birth outcomes.Results: This study included 59 patients in the cancer group for data analysis who had a history of malignancy. By matching, a total of 118 healthy infertile women were included in the control group. No statistically significant association was found in terms of age, duration of infertility, BMI, or insemination type between the two groups of patients. Thyroid cancer(45.8%) and gynecologic malignancies (44.07%) were the major cancer types in this study. There were statistically significant differences in the antral follicle count (AFC) (12.00 ± 7.86 vs. 14.90 ± 8.71, P=0.033), length of ovarian stimulation (9.98 ± 2.68 vs. 11.42 ± 2.43, P=0.033) and endometrial thickness on the trigger day (10.16 ± 3.11 vs. 10.84 ± 2.17, P0.05). There were no significant differences in the clinical pregnancy rate per ET cycle (32% vs. 40.39%, P=0.156), live birth rate per ET cycle (27% vs. 35.96%, P=0.119), miscarriage rate per ET cycle (5% vs. 4.43%, P=0.779), or preterm delivery rate per ET cycle (11.11% vs. 17.80%, P=0.547) between the two groups. Additionally, regression analysis showed that a history of malignancy was not a risk factor for reproductive outcomes.Conclusions: Overall, it is feasible for women with a history of cancer to conceive using ART is feasible and their long-term reproductive outcomes are similar to these of healthy infertile women. A history of cancer does not decrease the number of retrieved oocytes, increase the risk of adverse obstetric outcomes or affect birth outcomes.