Predicting in vitro fertilization success in the Brazilian public health system: a machine learning approach.

Infertility has become a global health problem, increasing the number of couples looking for in vitro fertilization (IVF). Despite advances and technical improvements, some couples remain childless due to the high complexity of the technique. The use of machine learning (ML) in the prediction of pregnancy, computing factors that could interfere in the effectiveness of the treatment, is an important tool to optimize these factors and reach the success of pregnancy. The aim of this study was to apply ML models to determine variables related to pregnancy after IVF in a public health service, including pre-implantation variables. This study included 771 women who underwent IVF treatment at Hospital das Clínicas, Federal University of Minas Gerais, between 2013 and 2019. We used the following Machine Learning algorithms: Logistic Regression, Random Forest, XG Boost and Support Vector Machines. The Random Forest algorithm achieved the best performance, with better accuracy, sensitivity and area under the ROC curve to predict the success of IVF evaluated by pregnancy frequency. We also trained a specific model only for women older than 35 years old. Variables in the Random Forest model related to pregnancy after in vitro fertilization.

Uterine alterations in women undergoing routine hysteroscopy before in vitro fertilization: high prevalence of unsuspected lesions.

OBJECTIVE: The aim of this study was to verify the prevalence of uterine cavity abnormalities diagnosed by routine office hysteroscopy in women preparing to IVF. METHODS: We carried out a retrospective cross-sectional study of 1141 consecutive women who underwent outpatient hysteroscopy before IVF at a tertiary academic center. Of these, 961 participants had a normal transvaginal sonography (TVS) of the uterine cavity. The prevalence of hysteroscopic alterations in successive age strata was submitted to Mantel-Haenzsel Chi-square test for linear trend. The diagnostic accuracy of TVS using hysteroscopy as reference was assessed by calculating the sensitivity, specificity, positive and negative likelihood ratios. RESULTS: Hysteroscopic alterations were present in 265/961 of patients with a negative TVS (prevalence 27.6%, 95% confidence interval [CI] 24.8%-30.5%). The prevalence of unsuspected submucous leiomyoma was higher among older women (p=0.005, chi-square test for linear trend) and reached 7.2% (95% CI 3.5%-14.1%) after 40 years. The sensitivity of TVS ranged from 8% (95% CI 2%-20%) for uterine synechiae to 41% (95% CI 28%-56%) for submucous leiomyoma, resulting in low likelihood ratios for negative TVS results. CONCLUSIONS: These findings suggest a high prevalence of unsuspected alterations found by routine hysteroscopy before IVF, an age-dependent increase in the frequency of submucous leiomyoma and a low diagnostic sensitivity of TVS to detect intracavitary lesions.

C-type natriuretic peptide signaling in human follicular environment and its relation with oocyte maturation.

Studies in mice have shown that C-type natriuretic peptide (CNP) is produced by granulosa cells and contributes to ovarian follicle growth and oocyte meiotic arrest until the preovulatory LH surge. In humans, the relationship between intraovarian CNP levels and oocyte meiotic resumption is unknown. The aim of this study was to investigate whether CNP and its receptor NPR2 are expressed in human ovarian follicles and if their levels change according to the meiotic phase of oocytes. We collected follicular fluid (FF) and luteinized granulosa cells (LGC) from follicle pools (n = 47), and FF, LGC and cumulus cells (CC) from individual follicles (n = 96) during oocyte pickup for in vitro fertilization. There was a positive linear correlation between CNP levels in FF pools and basal antral follicle counting (rs = 0.458; p = 0.002), number of preovulatory follicles >16 mm (rs = 0.361; p = 0.016) and number of oocytes retrieved (rs = 0,378; p = 0.011) and a negative correlation between CNP levels in FF pools and the percentage of mature (MII) oocytes retrieved (rs = -0.39; p = 0.033). FF CNP levels in follicles containing MII oocytes were significantly lower than in follicles containing immature (MI) oocytes (median = 0.44 vs. 0.57 ng/mL, p < 0.05). Accordingly, the CNP precursor gene NPPC was 50% less expressed in LGC from follicles containing MII oocytes than in follicles containing MI oocytes (p < 0.01). In addition, NPR2 mRNA was down-regulated in CC surrounding MII oocytes (60% reduction, p < 0.01). CNP signaling is downregulated in human ovarian follicles containing mature oocytes. Further studies should clarify whether CNP signaling is essential to keep oocyte meiotic arrest in humans.

Angiotensin-(1-7) in human follicular fluid correlates with oocyte maturation.

STUDY QUESTION: Do angiotensin (Ang)-(1-7) levels in human ovarian follicular fluid (FF) correlate with the number and proportion of mature oocytes obtained for IVF? SUMMARY ANSWER: The present study shows for the first time that Ang-(1-7) levels in human FF correlate with the proportion of mature oocytes collected upon ovarian stimulation for IVF. WHAT IS KNOWN ALREADY: Ang-(1-7) is an active peptide of the renin-angiotensin system that stimulates oocyte maturation in isolated rabbit and rat ovaries. However, its role in human ovulation remains unexplored. STUDY DESIGN, SIZE, DURATION: This was a prospective cohort study including 64 participants from a single IVF center. Sample size was calculated to achieve a statistical power of 80% in detecting 20% differences in the proportion of mature oocytes between groups. The participants were enrolled in the study during six consecutive months. PARTICIPANTS/MATERIALS, SETTING, METHODS: Plasma samples were obtained from all subjects at Day 21 of the last menstrual cycle before starting pituitary blockade and controlled ovarian stimulation (COS). Plasma and FF samples were quickly mixed with a protease inhibitor cocktail and stored at -80°C. Ang-(1-7) was quantified in plasma and FF samples by a highly sensitive and specific radioimmunoassay, which was preceded by solid phase extraction, speed vacuum concentration and sample reconstitution in assay buffer. FF Ang-(1-7) levels were stratified into tertiles and the patients of each tertile were compared for COS/IVF outcomes using Kruskal-Wallis ANOVA. Multiple regression analysis was used to adjust correlations for potential confounders. The mRNA encoding for Mas, a receptor for Ang-(1-7), was investigated by real-time PCR in luteinized granulosa cells purified from the FF. MAIN RESULTS AND THE ROLE OF CHANCE: There was a four-fold increase in plasma Ang-(1-7) after ovulation induction (median 160.9 vs 41.4 pg/ml, P < 0.0001). FF Ang-(1-7) levels were similar to (169.9 pg/ml) but did not correlate with plasma Ang-(1-7) levels (r = -0.05, P = 0.665). Patients at the highest FF Ang-(1-7) tertile had a higher proportion of mature oocytes compared to patients at the lower FF Ang-(1-7) tertile (median 100% vs 70%, P < 0.01). There was a linear correlation between FF Ang-(1-7) and the proportion of mature oocytes (r = 0.380, P < 0.01), which remained significant after adjustment for age and duration of infertility (r = 0.447, P < 0.001). The luteinized granulosa cells expressed Mas receptor mRNA, which was positively correlated to the number of mature oocytes in women with more than three mature oocytes retrieved (r = 0.42, P < 0.01). LIMITATIONS, REASONS FOR CAUTION: This is an observational study, therefore, no causal relationship can be established between Ang-(1-7) and human oocyte maturation. Mas protein expression was not quantified due to limited availability of granulosa cells. WIDER IMPLICATIONS OF THE FINDINGS: Since this peptide promotes oocyte maturation in other species, it deserves further investigation as a potential maturation factor to human oocytes. STUDY FUNDING AND COMPETING INTEREST(S): Research supported by Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) and Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG). The authors have nothing to disclose.

Expression of Nodal, Cripto, SMAD3, phosphorylated SMAD3, and SMAD4 in the proliferative endometrium of women with endometriosis.

BACKGROUND: Nodal is a growth factor of the transforming growth factor ß superfamily that is expressed in high turnover tissues, such as the human endometrium, and in several malignancies. The effects of Nodal are modulated by the coreceptor Cripto and mediated by SMAD proteins. This study evaluated the gene and protein expression of Nodal, Cripto, total and phosphorylated (p) SMAD3, and SMAD4 in the proliferative endometrium of women with and without endometriosis. METHOD: Total RNA was isolated and complementary DNA synthesized from eutopic endometrium of women with (n = 15) and without (n = 12) endometriosis, followed by quantitative real-time polymerase chain reaction (PCR) to evaluate the gene expression of Nodal, Cripto, SMAD3, and SMAD4. Western blot was used to evaluate the protein levels of Nodal and Cripto, and immunohistochemistry was performed to localize SMAD3, pSMAD3, and SMAD4. RESULTS: Although Nodal expression was unchanged in women with endometriosis, real-time PCR indicated lower gene expression of Cripto (fold change 0.27, P < .05) in the endometriosis group. This difference, however, was not maintained at protein expression level as assessed by Western blot. The immunostaining of total SMAD3 was reduced in the endometriosis group (P < .01), but the localization of pSMAD3 and the nuclear staining of SMAD4 were unchanged. CONCLUSION: These findings suggest that the Nodal signaling pathway has subtle changes in the endometrium of women with endometriosis, but this imbalance may not cause functional damage as it seems not to affect the nuclear expression of SMAD4.

Tissue specific localization of angiotensin-(1-7) and its receptor Mas in the uterus of ovariectomized rats.

The vasoactive peptide angiotensin (Ang)-(1-7) has vasodilator, antifibrotic and antihypertrophic properties, but little is known about its regulation in the uterus. The aim of this study was to evaluate Ang-(1-7) and its receptor Mas expression throughout rat uterine tissues, in ovariectomized animals treated with estrogen alone or combined with progestin. Adult Wistar rats (n = 19) were ovariectomized and randomly assigned into three different groups 1 week later. One group received a single dose of estradiol benzoate (1.5 mg/kg, i.m. injection, n = 6). Another group received estradiol associated with depot medroxyprogesterone acetate (3 mg/kg, i.m. injection, n = 6). Control group (n = 7) received oil injection. One week later, the rats were euthanized and their uteri were fixed and stained by immunohistochemistry, using a polyclonal antibody specific to Ang-(1-7) and its receptor Mas. Ang-(1-7) was detected in all uterine tissues, but it was weak or absent in the circular myometrium of treated animals. The intensity of the immunostaining decreased in the glandular epithelium of hormonally treated animals when compared to controls. In estrogen treated rats, Ang-(1-7) labeling was scattered and sometimes included the nuclei of glandular cells. We also detected Ang-(1-7) expression in longitudinal myometrium and uterine serosa. Mas receptor was present in all tissues with similar intensity among the tissue types in the control and estrogen plus progestin groups. In the estrogen group, Mas staining was stronger in the luminal and glandular epithelium when compared with stroma or circular myometrium. In conclusion, ovarian steroids are not required to allow endometrial expression of Ang-(1-7) and its receptor Mas in rats, as it remains abundant in ovariectomized animals. However, estrogen and progestin may modulate the distribution pattern of this peptide in the endometrium, especially in the glandular compartment.

Activin betaA subunit, follistatin and follistatin-like 3 are expressed in the endometrium of ovariectomized rats and regulated by estrogen replacement.

Activin A is a growth factor expressed in the endometrium, where it modulates tissue remodeling and enhances decidualization. The effects of activin A are counteracted by two binding proteins, namely follistatin and follistatin-like 3 (FSTL3). We have evaluated the effects of estrogen and progestin on the endometrial expression of activin betaA subunit, follistatin and FSTL3 in ovariectomized rats. Adult female Wistar rats (n = 21) were ovariectomized and received one week later a single dose of estradiol benzoate (1.5 mg/kg body weight, i.m. injection), either alone (n = 7) or associated with depot medroxyprogesterone acetate (3 mg/kg body weight, i.m. injection, n = 7), or oil vehicle (control group, n = 7). One week later, activin betaA subunit mRNA levels had increased significantly in the uteri of rats treated with estradiol alone (7.4 fold increase over controls, P < 0.05) and to the same extent in rats receiving estradiol plus medroxyprogesterone (6.1 fold increase over controls, P < 0.05). This was accompanied by increase of betaA subunit immunostaining in estradiol and estroprogestin treated rats, which was noted only in the surface endometrial epithelium. Follistatin mRNA expression, conversely, showed a significant decrease in the groups treated with estrogen alone and estrogen plus progestin (P < 0.05), and follistatin immunostaining in the glandular epithelium was weaker in estradiol and estroprogestin-treated rats compared to controls. FSTL3 expression was similar in the 3 groups. In conclusion, the expression of activin betaA subunit increases and that of follistatin decreases following estrogen replacement in the endometrium of ovariectomized rats, and these effects are not further altered by the addition of progestin.