Machine learning-based prediction of pregnancy outcomes in couples with non-obstructive azoospermia using micro-TESE for ICSI: a retrospective cohort study

Objective:To develop a clinically applicable tool for predicting clinical pregnancy,providing individualized patient counseling,and helping couples with non-obstructive azoospermia(NOA)decide whether to use fresh or cryopreserved spermatozoa for oocyte insemination before microdissection testicular sperm extraction(mTESE).Methods:A total of 240 couples with NOA who underwent mTESE-ICSI were divided into two groups based on the type of spermatozoa used for intracytoplasmic sperm injection(ICSI):the fresh and cryopreserved groups.After evaluating several machine learning algorithms,logistic regression was selected.Using LASSO regression and 10-fold cross-validation,the factors associated with clinical pregnancy were analyzed.Results:The area under the curves(AUCs)for the fresh and cryopreserved groups in the Logistic Regression-based prediction model were 0.977 and 0.759,respectively.Compared with various modeling algorithms,Logistic Regression outperformed machine learning in both groups,with an AUC of 0.945 for the fresh group and 0.788 for the cryopreserved group.Conclusion:The model accurately predicted clinical pregnancies in NOA couples.

Clinical application of the endometrial microbiota test combined with personalized treatment in patients with repeated implantation failure

Objective:The objective of this study was to investigate the clinical value of the endometrial microbiota test(EMT)combined with personalized treatment in patients with repeated implantation failure(RIF).Methods:From March 2019 to August 2022,the clinical data of patients with RIF at the Reproductive Medicine Research Center of the Sixth Affiliated Hospital of Sun Yat-sen University were retrospectively analyzed.A total of 356 patients underwent the EMT using 16S rRNA sequencing and were included in the EMT group.The SPSS statistical software propensity score was set at 1:1 to match the age,anti-Müllerian hormone(AMH),antral follicle count(AFC),years of infertility,and body mass index(BMI)of the women who had not undergone the EMT;subsequently,354 patients were classified in the non-EMT group.We compared the clinical characteristics of the two groups and analyzed the clinical pregnancy outcomes after personalized treatment.Results:The clinical pregnancy rate(CPR)of the EMT group was significantly higher than that of the non-EMT group(47.81%vs.13.38%,P<0.05).Among 356 patients who underwent the EMT,55 patients(15.45%)in group A with normal endometrial microbiota composition did not test positive for the pathogenic bacteria causing chronic endometritis,34 patients(9.55%)in group B with abnormal endometrial microbiota composition did not test positive for the pathogenic bacteria causing chronic endometritis,35 patients(9.83%)in group C with normal endometrial microbiota composition tested positive for the pathogenic bacteria causing chronic endometritis,and 232 patients(65.17%)in group D with abnormal endometrial microbiota composition tested positive for the pathogenic bacteria causing chronic endometritis.After administration of probiotics or antibiotic plus probiotics treatment,the pregnancy rates of groups C and D were higher than those of group A(44.00%vs.20.00%and 55.03%vs.20.00%,respectively;bothP<0.05).Conclusion:The EMT combined with personalized treatment in patients with RIF has solid clinical value as a new treatment strategy.