Machine learning approach to assess the association between anthropometric, metabolic, and nutritional status and semen parameters.

ABSTRACT: Many lifestyle factors, such as nutritional imbalance leading to obesity, metabolic disorders, and nutritional deficiency, have been identified as potential risk factors for male infertility. The aim of this study was to evaluate the relationship between semen parameters and anthropometric, metabolic and nutritional parameters. Relationship was first assessed individually, then after the application of a previously constructed and validated machine learning score that allows their combination. Anthropometric, metabolic, antioxidant, micronutrient, and sperm parameters from 75 men suffering from idiopathic infertility from four infertility centers in France (Jean-Verdier ART Center Hospital, Bondy; North Hospital ART Center, Saint-Étienne; Navarre Polyclinic ART Center, Pau; and Cochin Hospital ART Center, Paris) between September 2009 and December 2013 were collected. After assessing standard correlation analysis, a previously built machine learning model, providing a score ranging from 0 (the poorest) to 1 (the most favorable), was calculated for each man in the study cohort. This machine learning model, which separates infertile/fertile men with unexplained infertility on the basis of their bioclinical signature, provides a more holistic evaluation of the influence of the considered markers (anthropometric, metabolic, and oxidative status). We observed a significant correlation of some anthropometric, metabolic, and nutritional disorders with some sperm characteristics. Moreover, an unfavorable machine learning score was associated with a high level of sperm DNA fragmentation. Favorable anthropometric, metabolic, and oxidative patterns, which may reflect an appropriate lifestyle, appear to positively impact overall health, in particular reproductive function. This study, consistent with previous publications, suggests that beyond semen quality parameters, in an essential assessment of male fertility, other key factors should be taken into account. In this regard, the application of emerging artificial intelligence techniques may provide a unique opportunity to integrate all these parameters and deliver personalized care.

[Not unusual case of male genetic infertility]. / Infertilité masculine d'origine génétique : un cas pas si inhabituel.

Following a year of regular unprotected intercourse with his partner, and without achieving pregnancy, Mr. L. turned to his general practitioner. A semen analysis was carried out and no spermatozoa was found. After being referred to a male infertility specialist, the patient underwent a second test and a comprehensive assessment of his azoospermia. The azoospermia was confirmed and the genetic investigation revealed aneuploidy..

[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.

Combining metabolomics and machine learning models as a tool to distinguish non-classic 21-hydroxylase deficiency from polycystic ovary syndrome without adrenocorticotropic hormone testing.

STUDY QUESTION: Can a combination of metabolomic signature and machine learning (ML) models distinguish nonclassic 21-hydroxylase deficiency (NC21OHD) from polycystic ovary syndrome (PCOS) without adrenocorticotrophic hormone (ACTH) testing? SUMMARY ANSWER: A single sampling methodology may be an alternative to the dynamic ACTH test in order to exclude the diagnosis of NC21OHD in the presence of a clinical hyperandrogenic presentation at any time of the menstrual cycle. WHAT IS KNOWN ALREADY: The clinical presentation of patients with NC21OHD is similar with that for other disorders of androgen excess. Currently, cosyntropin stimulation remains the gold standard diagnosis of NC21OHD. STUDY DESIGN, SIZE, DURATION: The study was designed using a bicentric recruitment: an internal training set included 19 women with NC21OHD and 19 controls used for developing the model; a test set included 17 NC21OHD, 72 controls and 266 PCOS patients used to evaluate the performance of the diagnostic strategy thanks to an ML approach. PARTICIPANTS/MATERIALS, SETTING, METHODS: Fifteen steroid species were measured in serum by liquid chromatography-mass spectrometry (LC-MS/MS). This set of 15 steroids (defined as 'steroidome') used to map the steroid biosynthesis pathway was the input for our models. MAIN RESULTS AND THE ROLE OF CHANCE: From a single sample, modeling involving metabolic pathway mapping by profiling 15 circulating steroids allowed us to identify perfectly NC21OHD from a confounding PCOS population. The constructed model using baseline LC-MS/MS-acquired steroid fingerprinting successfully excluded all 17 NC21OHDs (sensitivity and specificity of 100%) from 266 PCOS from an external testing cohort of originally 549 women, without the use of ACTH testing. Blood sampling timing during the menstrual cycle phase did not impact the efficiency of our model. LIMITATIONS, REASONS FOR CAUTION: The main limitations were the use of a restricted and fully prospective cohort as well as an analytical issue, as not all laboratories are equipped with mass spectrometers able to routinely measure this panel of 15 steroids. Moreover, the robustness of our model needs to be established with a larger prospective study for definitive validation in clinical practice. WIDER IMPLICATIONS OF THE FINDINGS: This tool makes it possible to propose a new semiology for the management of hyperandrogenism. The model presents better diagnostic performances compared to the current reference strategy. The management of patients may be facilitated by limiting the use of ACTH tests. Finally, the modeling process allows a classification of steroid contributions to rationalize the biomarker approach and highlight some underlying pathophysiological mechanisms. STUDY FUNDING/COMPETING INTEREST(S): This study was supported by 'Agence Française de Lutte contre le dopage' and DIM Région Ile de France. This study was supported by the French institutional PHRC 2010-AOR10032 funding source and APHP. All authors declare no competing financial interests. TRIAL REGISTRATION NUMBER: N/A.

Identification of bronchoalveolar and blood immune-inflammatory biomarker signature associated with poor 28-day outcome in critically ill COVID-19 patients.

The local immune-inflammatory response elicited by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection is still poorly described, as well as the extent to which its characteristics may be associated with the outcome of critical Coronavirus disease 2019 (COVID-19). In this prospective monocenter study, all consecutive COVID-19 critically ill patients admitted from February to December 2020 and explored by fiberoptic bronchoscopy with bronchoalveolar lavage (BAL) were included. Biological assays, including digital ELISA cytokine profiling and targeted eicosanoid metabolomic analysis, were performed on paired blood and BAL fluid (BALF). Clinical outcome was assessed through the World Health Organization 10-point Clinical Progression Scale (WHO-CPS) at the 28th day (D28) following the admission to intensive care unit. A D28-WHO-CPS value higher than 5 defined a poor outcome. Seventy-six patients were included, 45 (59%) had a poor day-28 outcome. As compared to their counterparts, patients with D28-WHO-CPS > 5 exhibited a neutrophil-predominant bronchoalveolar phenotype, with a higher BALF neutrophil/lymphocyte ratio, a blunted local type I interferon response, a decompartimentalized immune-inflammatory response illustrated by lower BALF/blood ratio of concentrations of IL-6 (1.68 [0.30-4.41] vs. 9.53 [2.56-19.1]; p = 0.001), IL-10, IL-5, IL-22 and IFN-γ, and a biological profile of vascular endothelial injury illustrated by a higher blood concentration of VEGF and higher blood and/or BALF concentrations of several vasoactive eicosanoids. In critically ill COVID-19 patients, we identified bronchoalveolar and blood immune-inflammatory biomarker signature associated with poor 28-day outcome.

Standards of Genetic Testing in the Diagnosis and Prognostication of Systemic Mastocytosis in 2022: Recommendations of the EU-US Cooperative Group.

Mastocytosis comprises rare heterogeneous diseases characterized by an increased accumulation of abnormal mast cells in various organs/tissues. The pathogenesis of mastocytosis is strongly linked to the presence of KIT-activating mutations. In systemic mastocytosis (SM), the most frequent mutation encountered is KIT p.D816V, whose presence constitutes one of the minor diagnostic criteria. Different techniques are used to search and quantify the KIT p.D816V mutant; however, allele-specific quantitative PCR and droplet digital PCR are today the most sensitive. The analysis of the KIT p.D816V allele burden has undeniable interest for diagnostic, prognostic, and therapeutic monitoring. The analysis of non-mast cell hematological compartments in SM is similarly important because KIT p.D816V multilineage involvement is associated with a worse prognosis. In addition, in advanced forms of SM, mutations in genes other than KIT are frequently identified and affect negatively disease outcome and response to therapy. Thus, combined quantitative and sensitive analysis of KIT mutations and next-generation sequencing of other recurrently involved myeloid genes make it possible to better characterize the extent of the affected cellular compartments and additional molecular aberrations, providing a more detailed overview of the complex mutational landscape of SM, in relation with the clinical heterogeneity of the disease. In this article, we report the latest recommendations of the EU-US Cooperative Group presented in September 2020 in Vienna during an international working conference, on the techniques we consider standard to detect and quantify the KIT p.D816V mutant in SM and additional myeloid mutations found in SM subtypes.

A proof of concept of a machine learning algorithm to predict late-onset 21-hydroxylase deficiency in children with premature pubic hair.

In children with premature pubarche (PP), late onset 21-hydroxylase deficiency (21-OHD), also known as non-classical congenital adrenal hyperplasia (NCCAH), can be routinely ruled out by an adrenocorticotropic hormone (ACTH) test. Using liquid chromatography-tandem mass spectrometry (LC-MS/MS), a quantitative assay of the circulating steroidome can be obtained from a single blood sample. We hypothesized that, by applying multivariate machine learning (ML) models to basal steroid profiles and clinical parameters of 97 patients, we could distinguish children with PP from those with NCCAH, without the need for ACTH testing. Every child presenting with PP at the Trousseau Pediatric Endocrinology Unit between 2016 and 2018 had a basal and stimulated steroidome. Patients with central precocious puberty were excluded. The first set of patients (year 1, training set, n = 58), including 8 children with NCCAH verified by ACTH test and genetic analysis, was used to train the model. Subsequently, a validation set of an additional set of patients (year 2, n = 39 with 5 NCCAH) was obtained to validate our model. We designed a score based on an ML approach (orthogonal partial least squares discriminant analysis). A metabolic footprint was assigned for each patient using clinical data, bone age, and adrenal steroid levels recorded by LC-MS/MS. Supervised multivariate analysis of the training set (year 1) and validation set (year 2) was used to validate our score. Based on selected variables, the prediction score was accurate (100%) at differentiating premature pubarche from late onset 21-OHD patients. The most significant variables were 21-deoxycorticosterone, 17-hydroxyprogesterone, and 21-deoxycortisol steroids. We proposed a new test that has excellent sensitivity and specificity for the diagnosis of NCCAH, due to an ML approach.

Proof of concept and development of a couple-based machine learning model to stratify infertile patients with idiopathic infertility.

We aimed to develop and evaluate a machine learning model that can stratify infertile/fertile couples on the basis of their bioclinical signature helping the management of couples with unexplained infertility. Fertile and infertile couples were recruited in the ALIFERT cross-sectional case-control multicentric study between September 2009 and December 2013 (NCT01093378). The study group consisted of 97 infertile couples presenting a primary idiopathic infertility (> 12 months) from 4 French infertility centers compared with 100 fertile couples (with a spontaneously conceived child (< 2 years of age) and with time to pregnancy < 12 months) recruited from the healthy population of the areas around the infertility centers. The study group is comprised of 2 independent sets: a development set (n = 136 from 3 centers) serving to train the model and a test set (n = 61 from 1 center) used to provide an unbiased validation of the model. Our results have shown that: (i) a couple-modeling approach was more discriminant than models in which men's and women's parameters are considered separately; (ii) the most discriminating variables were anthropometric, or related to the metabolic and oxidative status; (iii) a refined model capable to stratify fertile vs. infertile couples with accuracy 73.8% was proposed after the variables selection (from 80 to 13). These influential factors (anthropometric, antioxidative, and metabolic signatures) are all modifiable by the couple lifestyle. The model proposed takes place in the management of couples with idiopathic infertility, for whom the decision-making tools are scarce. Prospective interventional studies are now needed to validate the model clinical use.Trial registration: NCT01093378 ALIFERT https://clinicaltrials.gov/ct2/show/NCT01093378?term=ALIFERT&rank=1 . Registered: March 25, 2010.

Clinical Impact of Inherited and Acquired Genetic Variants in Mastocytosis.

Mastocytosis is a rare and complex disease characterized by expansion of clonal mast cells (MC) in skin and/or various internal organ systems. Involvement of internal organs leads to the diagnosis of systemic mastocytosis (SM). The WHO classification divides SM into indolent SM, smoldering SM and advanced SM variants, including SM with an associated hematologic neoplasm, aggressive SM, and MC leukemia. Historically, genetic analysis of individuals with pure cutaneous mastocytosis (CM) and SM have focused primarily on cohort studies of inherited single nucleotide variants and acquired pathogenic variants. The most prevalent pathogenic variant (mutation) in patients with SM is KIT p.D816V, which is detectable in most adult patients. Other somatic mutations have also been identified-especially in advanced SM-in TET2, SRSF2, ASXL1, RUNX1, CBL and JAK2, and shown to impact clinical and cellular phenotypes. Although only small patient cohorts have been analyzed, disease associations have also been identified in several germline variants within genes encoding certain cytokines or their receptors (IL13, IL6, IL6R, IL31, IL4R) and toll-like receptors. More recently, an increased prevalence of hereditary alpha-tryptasemia (HαT) caused by increased TPSAB1 copy number encoding alpha-tryptase has been described in patients with SM. Whereas HαT is found in 3-6% of general Western populations, it is identified in up to 17% of patients with SM. In the current manuscript we review the prevalence, functional role and clinical impact of various germline and somatic genetic variants in patients with mastocytosis.

Wide-range CRP versus high-sensitivity CRP on Roche analyzers: focus on low-grade inflammation ranges and high-sensitivity cardiac troponin T levels.

Wide-range C-reactive protein (wr-CRP) has been proposed as an economical alternative to high-sensitivity C-reactive protein (hs-CRP) for the evaluation of low-grade inflammation-associated cardiovascular risk (LGI-CVR). Concomitant values of serum hs-CRP and plasma wr-CRP ≤5 mg/L, and high-sensitivity cardiac troponin T (hs-cTnT), all assayed on Roche Diagnostics analyzers over a 1.8-year period, were extracted from a hospital laboratory database. Hs-CRP and wr-CRP values were compared (Bland-Altman method; Deming's correlation), then separately classified into low (<1 mg/L), moderate (1-3 mg/L) and high (>3 mg/L) LGI-CVR ranges for agreement test (κ), assessed before and after Deming's regression-based adjustment of wr-CRP (Adj-wr-CRP). Wr-CRP and hs-CRP values were strongly correlated, with linearity, whether below 5 mg/L (n = 744; τ = 0.933; p < .001) or below 1 mg/L (n = 283; τ = 0.823; p < .001). Overall, wr-CRP values were lower than hs-CRP (mean bias: -0.11 ± 0.17 mg/L). Agreement was good, with 8.1% of wr-CRP values misclassified compared to hs-CRP (κ: 0.874), and weakly improved after regression-based adjustment (7.7% reclassified values; κ: 0.881). Lowering the Adj-wr-CRP cutoff of the moderate LGI-CVR subrange from 1.0 to 0.9 mg/L resulted in an almost perfect agreement (3.2% reclassified data; κ: 0.950). Hs-cTnT concentration was positively associated with hs-CRP, wr-CRP, and Adj-wr-CRP (p < .001). Within each LGI-CVR subrange, hs-cTnT medians were similar regardless of the hs-CRP, wr-CRP or Adj-wr-CRP used for risk classification. Based on hs-cTnT, this study supports the use of wr-CRP as a low-cost alternative to hs-CRP for cardiovascular risk evaluation.