Beyond black-box models: explainable AI for embryo ploidy prediction and patient-centric consultation.

PURPOSE: To determine if an explainable artificial intelligence (XAI) model enhances the accuracy and transparency of predicting embryo ploidy status based on embryonic characteristics and clinical data. METHODS: This retrospective study utilized a dataset of 1908 blastocyst embryos. The dataset includes ploidy status, morphokinetic features, morphology grades, and 11 clinical variables. Six machine learning (ML) models including Random Forest (RF), Linear Discriminant Analysis (LDA), Logistic Regression (LR), Support Vector Machine (SVM), AdaBoost (ADA), and Light Gradient-Boosting Machine (LGBM) were trained to predict ploidy status probabilities across three distinct datasets: high-grade embryos (HGE, n = 1107), low-grade embryos (LGE, n = 364), and all-grade embryos (AGE, n = 1471). The model's performance was interpreted using XAI, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) techniques. RESULTS: The mean maternal age was 38.5 ± 3.85 years. The Random Forest (RF) model exhibited superior performance compared to the other five ML models, achieving an accuracy of 0.749 and an AUC of 0.808 for AGE. In the external test set, the RF model achieved an accuracy of 0.714 and an AUC of 0.750 (95% CI, 0.702-0.796). SHAP's feature impact analysis highlighted that maternal age, paternal age, time to blastocyst (tB), and day 5 morphology grade significantly impacted the predictive model. In addition, LIME offered specific case-ploidy prediction probabilities, revealing the model's assigned values for each variable within a finite range. CONCLUSION: The model highlights the potential of using XAI algorithms to enhance ploidy prediction, optimize embryo selection as patient-centric consultation, and provides reliability and transparent insights into the decision-making process.

Short androgen receptor poly-glutamine-promoted endometrial cancer is associated with benzo[a]pyrene-mediated aryl hydrocarbon receptor activation.

The androgen receptor (AR) poly-glutamine polymorphism (AR-Q) was reported to play role in endometrial cancer (EMCA) development, yet controversial. Environmental factors interact with genetic variation have been reported in EMCA. Aerosol toxins, polycyclic aromatic hydrocarbon benzo[a]pyrene (BaP), are EMCA facilitators. This report examined the interplay between AR-Qs and BaP in EMCA. During analysing patient AR-Q polymorphism and Aryl hydrocarbon Receptor (AhR) expressions, we found overall survival (OS) benefit is ascending with AR-Q lengths (5-year OS of 61.3% in Q length <20 and 88% in Q length >23). And AhR is higher expressed in short AR-Q tumour compared to that in long AR-Q patient. In vitro study found androgen-response element (ARE) activity descends with AR-Qs length (Q13 > Q25 > Q35), whereas BaP suppresses ARE activities in EMCA cells. Furthermore, AR-Q13 (but not AR-Q25, or -35) enhances BaP-induced dioxin-responsive element (DRE) activity. Lastly, AR-Q13 exerts higher colony-forming capacity than other AR-Qs, and knock-down AhR abolished AR-Q13-mediated colony numbers. This study demonstrated a possible interaction of gene (AR-Q polymorphism) and environmental toxins (e.g. BaP) to affect cancer progression. A large-scale epidemiology and public health survey on the interaction of environmental toxin and AR poly-Q in EMCA is suggested.

Cholesterol import and steroidogenesis are biosignatures for gastric cancer patient survival.

Androgens, estrogens, progesterone and related signals are reported to be involved in the pathology of gastric cancer. However, varied conclusions exist based on serum hormone levels, receptor expressions, and in vitro or in vivo studies. This report used a web-based gene survival analyzer to evaluate biochemical processes, including cholesterol importing via lipoprotein/receptors (L/R route), steroidogenic enzymes, and steroid receptors, in gastric cancer patients prognosis. The sex hormone receptors (androgen receptor, progesterone receptor, and estrogen receptor ESR1 or ESR2), L/R route (low/high-density lipoprotein receptors, LDLR/LRP6/SR-B1 and lipoprotein lipase, LPL) and steroidogenic enzymes (CYP11A1, HSD3B1, CYP17, HSD17B1, HSD3B1, CYP19A1 and SRD5A1) were associated with 5-year survival of gastric cancer patients. The AR, PR, ESR1 and ESR2 are progression promoters, as are the L/R route LDLR, LRP6, SR-B1 and LPL. It was found that CYP11A1, HSD3B1, CYP17, HSD17B1 and CYP19A1 promote progression, but dihydrotestosterone (DHT) converting enzyme SRD5A1 suppresses progression. Analyzing steroidogenic lipidome with a hazard ratio score algorithm found that CYP19A1 is the progression confounder in surgery, HER2 positive or negative patients. Finally, in the other patient cohort from TCGA, CYP19A1 was expressed higher in the tumor compared to that in normal counterparts, and also promoted progression. Lastly, exemestrane (type II aromatase inhibitor) dramatically suppress GCa cell growth in pharmacological tolerable doses in vitro. This work depicts a route-specific outside-in delivery of cholesterol to promote disease progression, implicating a host-to-tumor macroenvironmental regulation. The result indicating lipoprotein-mediated cholesterol entry and steroidogenesis are GCa progression biosignatures. And the exemestrane clinical trial in GCa patients of unmet medical needs is suggested.

Effect of premature serum progesterone rise on embryo transfer outcomes and the role of blastocyst culture and transfer in assisted reproductive technology cycles with premature progesterone rise.

OBJECTIVE: In 1991, researchers reported that a modest preovulatory increase in serum progesterone levels is associated with lower pregnancy rates and higher incidence of pregnancy loss in in vitro fertilization (IVF). We wonder whether embryo transfer (ET) in assisted reproductive technology (ART) cycles in patients with premature progesterone rise (PPR) have a negative impact on the clinical pregnancy rates (CPRs) and/or live birth rates (LBRs) in our series. Consequently, will blastocyst transfer reverse the negative impact? MATERIALS AND METHODS: This noninterventional, retrospective, observational tertiary center study was conducted between January 2010 and December 2012. All fresh ET cycles with serum progesterone levels measured (n = 599) on the day of hCG administration were analyzed. RESULTS: Sera lutenizing hormone (LH), E2, and progesterone (P) were measured and analyzed. The CPRs of cycles in patients with p ≤ 1.5 ng/mL (low) versus those with p > 1.5 ng/mL (high) were 37.04% versus 41.03% [odds ratio (OR) = 1.18, 95% confidence interval (CI): 0.728-1.920; p = 0.50). The LBRs of cycles in patients with low progesterone level versus those with PPR were 30.52% versus 34.62% (OR = 1.21, 95% CI: 0.729-1.992; p = 0.47). No statistically significant association was detected. We further analyzed the outcomes according to different stages of ET and found that blastocyst (D5) ET significantly increase the LBRs as compared with cleavage stage (D2/D3) ET in the PPR group (44.44% versus 21.43%; p = 0.043). CONCLUSION: PPR did not significantly compromise the clinical outcomes in this series. However, shifting to blastocyst transfer probably could increase the live birth in cycles with PPR.

Expression of apoptotic factors in vaginal tissues from women with urogenital prolapse.

AIMS: Increased apoptotic activity in pelvic tissues may contribute to development of pelvic floor disorders. We evaluated expression of apoptotic factors (Bcl-2 family) in vaginal tissues from women with pelvic organ prolapse (POP) and how these factors correlate with severity of prolapse. METHODS: mRNA and protein expression of anti-apoptotic and pro-apoptotic factors in vaginal tissues from subjects and controls were determined by real-time PCR and Western blot. Severity of prolapse was staged using POP-Q criteria. RESULTS: Differential expression of Bcl-2 family factors was observed in protein rather than in gene expression. During the secretory phase, the anti-apoptotic (Bcl-2, Bcl-xl) and pro-apoptotic protein (Bax) were upregulated in controls compared to cases (P < 0.05). The ratios of Bcl-2/Bax and Bcl-2/Bad, which determine cellular sensitivity to induction of apoptosis, were higher in controls versus cases. Higher ratios indicate reduced cellular sensitivity to apoptosis. Protein expression of Bax and Bad was higher in women with severe compared to mild prolapse (P < 0.05). CONCLUSION: Increased expression of Bad, Bax, and decreased ratios of Bcl-2/Bax, Bcl-2/Bad suggest increased apoptotic activity or sensitivity to induction of apoptosis in vaginal tissues of women with POP.

Is lysyl oxidase-like protein-1, alpha-1 antitrypsin, and neutrophil elastase site specific in pelvic organ prolapse?

INTRODUCTION AND HYPOTHESIS: We investigated whether the expression of alpha-1 antitrypsin (ATT), neutrophil elastase (NE), and lysyl oxidase-like protein 1 (LOXL-1) vary within the vagina in subjects with pelvic organ prolapse (POP). METHODS: Biopsies were obtained from the anterior and posterior vaginal wall of 22 women with POP (> or =stage 2 by POP-Q). The subjects were grouped by the most prominent defect: cystocele, cystocele plus uterine prolapse, and rectocele. Comparative real-time PCR, Western blotting, and NE enzyme activity assay were performed. RESULTS: The ratio of anterior and posterior vaginal wall ATT, NE, and LOXL-1 expression varied between individuals within the same defect group. CONCLUSIONS: ATT, NE, and LOXl-1 expression was variable among different biopsy sites in the vagina. No consistent pattern was present when the subjects were grouped by the most prominent defect. We recommend careful consideration of biopsy sites in future studies on POP to enhance reproducibility of data.

Prenatal diagnosis of isolated fetal hydrocolpos secondary to congenital imperforate hymen.

A 32-year-old primigravida was referred to our hospital at 36 weeks of gestation with a fetal pelvic mass. Ultrasonography showed the fluid-filled area to be a 9 x 4 x 5-cm pear-shaped retrovesical mass with a funnel-shaped blind pouch at the distal end of the fetal vagina. Marked left hydronephrosis resulting from mass compression was also detected. Fetal magnetic resonance imaging further defined a pelvic lesion extending cephalically into the abdomen and caudally into the vagina. Membranal protrusion of the introitus was clearly identified. Therefore, the diagnosis of congenital imperforate hymen with hydrocolpos was established. At 38 weeks of gestation, a 2,966-g female infant was delivered vaginally with good Apgar scores. Physical examination of the neonate revealed a bulging membrane covering the vaginal opening. The presence of syndromic disorders (McKusick-Kaufman, Ellis-van Creveld or Bardet-Biedl syndromes), genitourinary and anorectal anomalies were excluded. The karyotype was 46,XX. A hymenotomy was performed on the second day of life. The infant recovered fully after hymenotomy.

Mitochondria transfer can enhance the murine embryo development.

PURPOSE: To evaluate the effect of mitochondrial transfer on embryonic development. MATERIALS AND METHODS: Mitochondria concentrates were collected from murine hepatocytes and fertilized murine zygotes from young and older mice in the 2PN stage were subjected to mitochondrial transfer and cultured in vitro to evaluate the embryonic development. RESULTS: After extended in vitro culture, 37.65% and 20.91% embryos from the young mice developed to the blastocyst stage in the injected and control groups respectively, which is statistically significant. There was no difference in terms of hatching rates (1.76% and 1.82% respectively). Zygotes from the older mice (>20 weeks old) that received mitochondrial transfer also had a better developmental outcome than the control group (54.35% and 18.92% developed to morula stage, 43.48% and 8.11% developed to the blastocyst stage respectively), which is statistically significant. CONCLUSIONS: Our results for the murine model provide direct scientific evidence that mitochondrial transfer improves embryonic development. However, potential risks such as mitochondrial heteroplasmy, nuclear-mitochondrial interaction and epigenetic aspects all deserve further evaluation before mitochondrial transfer is applied clinically.

Differential effects of oral conjugated equine estrogen and transdermal estrogen on atherosclerotic vascular disease risk markers and endothelial function in healthy postmenopausal women.

BACKGROUND: Recent studies have revealed that HRT may increase the risk for atherosclerotic vascular disease (ASVD). METHODS: We investigated the effects of HRT via different administration routes on the markers for ASVD and endothelial function in healthy postmenopausal women. The oral HRT group (n=18) received conjugated equine estrogen 0.625 mg/day; the transdermal HRT group (n=18) received 17beta-estradiol (E2) gel 0.6 mg/day for 6 months. The control group (n=30) had no treatment for 6 months. RESULTS: The C-reactive protein (CRP) rose from 0.129+/-0.116 to 0.752+/-0.794 mg/dl (P<0.01) in the oral HRT group but remained unchanged in the transdermal HRT and control groups. The flow-mediated vasodilation (FMD) in the brachial artery was increased significantly by HRT from 6.0% before oral HRT to 14.7% after oral HRT (P<0.001) and from 5.9% before transdermal HRT to 13.9% after transdermal HRT (P=0.001). CONCLUSIONS: These data suggest that oral estrogen induces ASVD risk by increasing acute inflammation; however, transdermal estrogen avoids this untoward effect. Additionally, transdermal estrogen exerts a positive effect on endothelial function similar to that of oral estrogen. Therefore, the transdermal route might be favourable in terms of ASVD risks.

The serum follicle-stimulating hormone-to-luteinizing hormone ratio at the start of stimulation with gonadotropins after pituitary down-regulation is inversely correlated with a mature oocyte yield and can predict "low responders".

OBJECTIVE: The aim of this study was to investigate the relationship of serum FSH and LH levels at the commencement of stimulation to ovarian follicular development in women undergoing pituitary down-regulation and controlled ovarian hyperstimulation with gonadotropins in IVF or intracytoplasmic sperm injection (ICSI) cycles. DESIGN: Retrospective analysis. SETTING: An IVF program in a tertiary medical center. PATIENT(S): A total of 245 women proven to be pituitary down-regulated by their serum E(2) levels. INTERVENTION(S): Patients treated with a GnRH agonist and FSH and hMG underwent assisted reproductive technique (ART). MAIN OUTCOME MEASURE(S): Mature oocyte yield, pregnancy rate (PR), and live birth rate. RESULT(S): The serum FSH levels and the FSH-to-LH ratio at the commencement of gonadotropin stimulation were inversely correlated to the number of mature oocytes (r = -0.193 and r = -0.224, respectively). When assessed with receiver-operating characteristic (ROC) analysis, there was statistically significant ability for the FSH/LH ratio to differentiate between the "poor response" cycles (with mature oocyte yield < or =4) and the normal response cycles. Using the cutoff value derived from ROC analysis, cycles with the FSH-to-LH ratio > or =3 produced less mature oocytes (8.25 vs. 11.74), lower peak E(2) levels (1,975.3 pg/mL vs. 3,324.8 pg/mL), and higher percentage of poor ovarian response cycles (32.5% vs. 14.3%). CONCLUSION(S): The serum FSH-to-LH ratio at the start of gonadotropin stimulation after pituitary down-regulation provided a practical method for early prediction of mature oocyte yield.

The effect of preincubation period of oocytes on nuclear maturity, fertilization rate, embryo quality, and pregnancy outcome in IVF and ICSI.

PURPOSE: To clarify the effect of preincubation of oocytes on the results of IVF and ICSI. METHODS: A total of 176 IVF and 64 ICSI cycles received long protocol ovarian stimulation. The oocytes were incubated for 1-8 h before insemination or sperm injection. Metaphase II (MII) percentage was evaluated in the ICSI arm; fertilization rates, embryo quality, and pregnancy outcomes were analyzed in both IVF and ICSI arms according to the preincubation period duration of oocytes. RESULTS: The MII percentage of the ICSI arm was significantly lower (P < 0.05) in the group with preincubation period of < 2.5 h. The fertilization rates in groups with preincubation for 2.5-5.5 h were significantly higher (P < 0.001) for IVF. Embryo quality and pregnancy outcomes were not significantly different between the IVF or ICSI arm. CONCLUSIONS: The preincubation of oocytes for at least 2.5 h is beneficial to both IVF and ICSI outcomes by increasing the nuclear maturity of oocytes.