[Artificial intelligence: to a better predictive strategy for testicular sperm extraction outcome in azoospermia]. / Intelligence artificielle : vers une meilleure stratégie de prédiction du résultat de la biopsie testiculaire dans un contexte d'azoospermie.

Azoospermia, defined as the absence of sperm in the semen, is found in 10-15 % of infertile patients. Two-thirds of these cases are caused by impaired spermatogenesis, known as non-obstructive azoospermia (NOA). In this context, surgical sperm extraction using testicular sperm extraction (TESE) is the best option and can be offered to patients as part of fertility preservation, or to benefit from in vitro fertilization. The aim of the preoperative assessment is to identify the cause of NOA and evaluate the status of spermatogenesis. Its capacity to predict TESE success remains limited. As a result, no objective and reliable criteria are currently available to guide professionals on the chances of success and enable them to correctly assess the benefit-risk balance of this procedure. Artificial intelligence (AI), a field of research that has been rapidly expanding in recent years, has the potential to revolutionize medicine by making it more predictive and personalized. The aim of this review is to introduce AI and its key concepts, and then to examine the current state of research into predicting the success of TESE.

Mechanics of human embryo compaction.

The shaping of human embryos begins with compaction, during which cells come into close contact1,2. Assisted reproductive technology studies indicate that human embryos fail compaction primarily because of defective adhesion3,4. On the basis of our current understanding of animal morphogenesis5,6, other morphogenetic engines, such as cell contractility, could be involved in shaping human embryos. However, the molecular, cellular and physical mechanisms driving human embryo morphogenesis remain uncharacterized. Using micropipette aspiration on human embryos donated to research, we have mapped cell surface tensions during compaction. This shows a fourfold increase of tension at the cell-medium interface whereas cell-cell contacts keep a steady tension. Therefore, increased tension at the cell-medium interface drives human embryo compaction, which is qualitatively similar to compaction in mouse embryos7. Further comparison between human and mouse shows qualitatively similar but quantitively different mechanical strategies, with human embryos being mechanically least efficient. Inhibition of cell contractility and cell-cell adhesion in human embryos shows that, whereas both cellular processes are required for compaction, only contractility controls the surface tensions responsible for compaction. Cell contractility and cell-cell adhesion exhibit distinct mechanical signatures when faulty. Analysing the mechanical signature of naturally failing embryos, we find evidence that non-compacting or partially compacting embryos containing excluded cells have defective contractility. Together, our study shows that an evolutionarily conserved increase in cell contractility is required to generate the forces driving the first morphogenetic movement shaping the human body.

[The revision of the Bioethics Act, two years on: major principles and consequences for practice in the reproductive biology laboratory]. / La révision de la loi de bioéthique, deux ans après : grands principes et conséquences pour la pratique au laboratoire de biologie de la reproduction.

Since 1994, in France, bioethics law has set the regulatory framework for Medically Assisted Reproduction (MAR). The latest revision of the law of August 2, 2021, is characterized by major upheavals in the field of MAR and intervenes in several areas: the purpose and conditions to access to MAR, access to origins in the case of gamete or embryo donation, and gametes cryopreservation without medical indication. Indeed, the law authorizes, because of a strong societal demand, the extension of sperm donation to couples of women and unmarried women, as well as the possibility for any person to preserve his/her gametes if he/she meets the age criteria defined by decree. Finally, the law opens the possibility for people born following gamete or embryo donation to have access, from their 18th anniversary, to identifying and/or non-identifying data. These new measures have led to a very important number of MAR requests to fertility and donation centers, and have required the implementation of new circuits in order to harmonize care, without discrimination or prioritization.

A Machine Learning Approach for the Prediction of Testicular Sperm Extraction in Nonobstructive Azoospermia: Algorithm Development and Validation Study.

BACKGROUND: Testicular 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. OBJECTIVE: The 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. METHODS: We 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. RESULTS: The 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. CONCLUSIONS: An 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.

Rapid diagnosis of cryptococcosis using an antigen detection immunochromatographic test.

OBJECTIVES: Current methods for cryptococcal antigen detection have some limitations. This study aimed at evaluating a lateral flow assay (LFA) for the diagnosis of cryptococcosis in a French University medical center. METHODS: A retrospective study was performed on samples collected from patients with a definitive diagnosis of cryptococcosis (group I 66 samples; 28 patients) or with non-Cryptococcus invasive fungal infection (group II 18 samples; 17 patients). In addition, 274 samples from 205 consecutive patients, either suspected of cryptococcal infection or routinely screened during their follow-up, were prospectively tested (group III). Cryptococcal antigen was assayed using LFA and an EIA. A latex-based test was used for confirmation. RESULTS: Sensitivity calculated on group I and specificity on group II, were respectively at 100% and 90.0%. Two false positives were related to Trichosporon fungemia. Per-sample analysis on group III revealed sensitivity, specificity, positive and negative predictive values all at 100% for CSF, and at 100%, 98.9%, 75% and 100%, respectively for serum samples. LFA enabled the diagnosis of two cases of asymptomatic cryptococcosis. CONCLUSION: The excellent diagnostic value and practicality (visual reading results in 15 min) of LFA make it fully appropriate for the diagnosis of cryptococcosis in this particular setting.