Search

BackgroundTesticular sperm extraction (TESE) is an essential therapeutic tool for the management of male infertility. However, it is an invasive procedure with a success rate up to 50%. To date, no model based on clinical and laboratory parameters is sufficiently powerful to accurately predict the success of sperm retrieval in TESE. ObjectiveThe aim of this study is to compare a wide range of predictive models under similar conditions for TESE outcomes in patients with nonobstructive azoospermia (NOA) to identify the correct mathematical approach to apply, most appropriate study size, and relevance of the input biomarkers. MethodsWe analyzed 201 patients who underwent TESE at Tenon Hospital (Assistance Publique-Hôpitaux de Paris, Sorbonne University, Paris), distributed in a retrospective training cohort of 175 patients (January 2012 to April 2021) and a prospective testing cohort (May 2021 to December 2021) of 26 patients. Preoperative data (according to the French standard exploration of male infertility, 16 variables) including urogenital history, hormonal data, genetic data, and TESE outcomes (representing the target variable) were collected. A TESE was considered positive if we obtained sufficient spermatozoa for intracytoplasmic sperm injection. After preprocessing the raw data, 8 machine learning (ML) models were trained and optimized on the retrospective training cohort data set: The hyperparameter tuning was performed by random search. Finally, the prospective testing cohort data set was used for the model evaluation. The metrics used to evaluate and compare the models were the following: sensitivity, specificity, area under the receiver operating characteristic curve (AUC-ROC), and accuracy. The importance of each variable in the model was assessed using the permutation feature importance technique, and the optimal number of patients to include in the study was assessed using the learning curve. ResultsThe ensemble models, based on decision trees, showed the best performance, especially the random forest model, which yielded the following results: AUC=0.90, sensitivity=100%, and specificity=69.2%. Furthermore, a study size of 120 patients seemed sufficient to properly exploit the preoperative data in the modeling process, since increasing the number of patients beyond 120 during model training did not bring any performance improvement. Furthermore, inhibin B and a history of varicoceles exhibited the highest predictive capacity. ConclusionsAn ML algorithm based on an appropriate approach can predict successful sperm retrieval in men with NOA undergoing TESE, with promising performance. However, although this study is consistent with the first step of this process, a subsequent formal prospective multicentric validation study should be undertaken before any clinical applications. As future work, we consider the use of recent and clinically relevant data sets (including seminal plasma biomarkers, especially noncoding RNAs, as markers of residual spermatogenesis in NOA patients) to improve our results even more.

Objective The objective of our study was to determine the main surgical factors associated with postoperative pains in patients undergoing adnexectomy. Material and Methods Patients that underwent adnexectomy in two French Gynecological centers between July, 2018 and March, 2020 were prospectively included and retrospectively analyzed. The main pre and per operative surgical factors were analyzed to assess their impact on immediate postoperative pain. Analgesic consumption was recorded for each patient and pain was evaluated using the validated numeric rating scale (ranging between 0 and 10). Results One hundred and seventeen patients underwent laparoscopic adnexectomy. Eighty-four patients (72%) experienced either no or minor postoperative pain (NRS ≤ 2). Seventeen patients (14.5%) required strong opioids (subcutaneous morphine injection) in the immediate postoperative period. The only two parameters that had a significant impact on immediate postoperative pain were the realization of a fascia closure and the duration of pneumoperitoneum longer than 60 minutes. Pneumoperitoneum pressure and size of ports were not significantly correlated with postoperative pain. Conclusion Fascia closure and increased surgical time were significantly associated with immediate postoperative pain and the need for strong opioids consumption. Surgical training to limit prolonged surgeries should be strongly emphasized to lower postoperative pain and limit opioids consumption.

Endometriosis is an inflammatory oestrogen-dependent chronic disease and is mainly expressed by pain and increased infertility. Several studies showed an increased prevalence of autoimmune systemic diseases and various autoantibodies in endometriosis. The association of these autoimmune markers and diseases could raise the fact that endometriosis is an authentic autoimmune or inflammatory disease and thus could argue for the use of immunomodulatory therapies. Usually, it is considered that the autoantibodies did not directly act in endometrium implants growth, and could be rather implicated in endometriosis-related infertility. The use of immunomodulatory strategies could be an important alternative or additional strategy to the use of hormones and surgery but need prospective well-designed trials.