Machine learning models predicts risk of proliferative lupus nephritis.

Objective: This study aims to develop and validate machine learning models to predict proliferative lupus nephritis (PLN) occurrence, offering a reliable diagnostic alternative when renal biopsy is not feasible or safe. Methods: This study retrospectively analyzed clinical and laboratory data from patients diagnosed with SLE and renal involvement who underwent renal biopsy at West China Hospital of Sichuan University between 2011 and 2021. We randomly assigned 70% of the patients to a training cohort and the remaining 30% to a test cohort. Various machine learning models were constructed on the training cohort, including generalized linear models (e.g., logistic regression, least absolute shrinkage and selection operator, ridge regression, and elastic net), support vector machines (linear and radial basis kernel functions), and decision tree models (e.g., classical decision tree, conditional inference tree, and random forest). Diagnostic performance was evaluated using ROC curves, calibration curves, and DCA for both cohorts. Furthermore, different machine learning models were compared to identify key and shared features, aiming to screen for potential PLN diagnostic markers. Results: Involving 1312 LN patients, with 780 PLN/NPLN cases analyzed. They were randomly divided into a training group (547 cases) and a testing group (233 cases). we developed nine machine learning models in the training group. Seven models demonstrated excellent discriminatory abilities in the testing cohort, random forest model showed the highest discriminatory ability (AUC: 0.880, 95% confidence interval(CI): 0.835-0.926). Logistic regression had the best calibration, while random forest exhibited the greatest clinical net benefit. By comparing features across various models, we confirmed the efficacy of traditional indicators like anti-dsDNA antibodies, complement levels, serum creatinine, and urinary red and white blood cells in predicting and distinguishing PLN. Additionally, we uncovered the potential value of previously controversial or underutilized indicators such as serum chloride, neutrophil percentage, serum cystatin C, hematocrit, urinary pH, blood routine red blood cells, and immunoglobulin M in predicting PLN. Conclusion: This study provides a comprehensive perspective on incorporating a broader range of biomarkers for diagnosing and predicting PLN. Additionally, it offers an ideal non-invasive diagnostic tool for SLE patients unable to undergo renal biopsy.

A noninvasive method for the detection of foetal DNA in early pregnancy based on differential methylation pattern of Ras association domain family member 1A.

BACKGROUND: The detection of foetal DNA and extravillus trophoblasts (EVTs) in early pregnancy in cervical and uterine samples offers a potential pathway for non-invasive prenatal diagnostics. However, the challenge lies in effectively quantifying these samples. This study introduces a novel approach using the Ras association domain family 1 A (RASSF1A), which exhibits hypermethylation in foetal cells and hypomethylation in maternal cells. The differential methylation pattern of RASSF1A provides a unique biomarker for quantifying foetal cells in cervical and intrauterine samples. METHODS: This study was conducted between September 2022 and May 2023. In total, 23 samples (12 cervical cell samples and 11 intrauterine samples) were collected from women in the Sichuan Jinxin Women & Children Hospital, Jingxiu District, Chengdu, China. The cervical cell samples were collected via lavage and brush techniques, and the intrauterine cell samples were obtained via uterine lavage. These samples were collected as part of a broader effort to advance our understanding of foetal cell dynamics during early pregnancy. The sampling methods were chosen for their minimally invasive nature and their potential in capturing a representative cell population from the respective sites. After digestion of the cell samples using a methylation-sensitive restriction enzyme cocktail, a critical step to differentiate between maternal and foetal DNA, the quantitative polymerase chain reaction (qPCR) of RASSF1A and ß-actin (ACTB) were employed to measure foetal DNA and cell concentrations. Immunofluorescence techniques targeting histocompatibility complex, class I G (HLA-G) and GATA binding protein 3 (GATA-3) were employed to detect EVTs in the cell samples and in decidual tissue, with the latter providing an additional layer of confirmation for the presence of foetal cells. RESULTS: The results showed no hypermethylated RASSF1A was detected in any of the cervical samples, irrespective of whether the samples were obtained by brush or lavage. However, an average of 17,236 ± 7490 foetal cells per sample were detected in the uterine lavage samples. Foetal cells accounted for approximately 0.14% ± 0.10% of the total cell population in these samples. The presence of EVTs in these samples was confirmed by their expression of both HLA-G and GATA-3. CONCLUSION: The detection of foetal cells in uterine cavity samples based on hypermethylation of RASSF1A and quantification of foetal cells can be used to prenatal screening. GATA-3 can be used to label EVTs.

In the realm gestational foetal health, obtaining foetal cells or genetic information is important for detecting and managing potential genetic disorders. Although foetal cells can be obtained from the cervix or uterine cavity, methods to quantify the foetal cell and foetal DNA are lacking. We introduce an innovative technique that utilises DNA restriction endonucleases to selectively isolate foetal DNA and identify foetal cells. We used this technique to measure the number of foetal cells in a sample. Using this technique, we detected foetal cells collected via lavage in uterine but not cervical samples. This finding is significant as it paves the way towards early detection of chromosomal disorders in foetuses, potentially as early as the 10th week of pregnancy. Such early detection offers promising new screening options in early pregnancy, contributing to better prenatal care and outcomes.

Dysregulated low-density granulocyte contributes to early spontaneous abortion.

Spontaneous abortion (SA) is a common adverse pregnancy event with unclarified pathogenesis and limited therapeutic efficiency. Although most SA cases with the euploid embryo(s) are associated with immunological factors, the contribution of low-density granulocyte (LDG) in SA pathogenesis is rarely reported. This study aimed to investigate the serial characteristics and possible contribution of LDG and their subpopulations in early pregnancy, especially in early SA. Unpregnant (UP), normally pregnant (NP), and SA women were recruited, and the peripheral blood and endometrium/decidua were collected for LDG isolation and histological observation. The percentage, phenotype, and subpopulations of LDG were analyzed via flow cytometric analysis, and the ability of Nets formation was assessed by immunofluorescent and immunohistochemical assays. As a result, 43 participants were enrolled, including 10 UP, 15 NP, and 18 SA women. Compared with the UP group, the LDG percentage in peripheral blood mononuclear cells (PBMCs) and decidual immune cells (DICs) increased in the NP group, while the loss of this increase was observed in the SA group. Meanwhile, CD16int/- cell percentage in peripheral blood LDG (PB-LDG) increased in the NP and SA groups, and insufficient activation of CD16hi PB-LDG characterized by reduced CD11b expression was discovered in the SA group. Moreover, the LDG percentage in DICs was higher than that in PBMCs, and the decidual LDG (D-LDG) showed a surface marker expression profile that is easier to be activated in the pregnant cohort (NP + SA women). Finally, increased decidual Nets formation was observed in the SA group compared with the NP group, and more Nets formation was detected in D-LDG of NP and SA women following PMA stimulation. Overall, LDG participates in the maintenance of early pregnancy, while dysregulated LDG is responsible for early SA, providing novel potential targets for further exploration of SA pathogenesis and therapeutics.

Comparison of the Effectiveness of Endometrial Receptivity Analysis (ERA) to Guide Personalized Embryo Transfer with Conventional Frozen Embryo Transfer in 281 Chinese Women with Recurrent Implantation Failure.

BACKGROUND This study aimed to compare the effectiveness of endometrial receptivity analysis (ERA)-guided personalized embryo transfer (pET) with conventional frozen embryo transfer (FET) in 281 Chinese women with recurrent implantation failure (RIF). MATERIAL AND METHODS A total of 281 eligible patients with RIF were recruited and assigned to ERA (ERA followed by pET) and FET groups. The clinical pregnancy outcomes were compared between the 2 groups. RESULTS There were no significant differences between the ERA and FET groups in terms of endometrial thickness on the day of embryo transfer, mean attempts of assisted reproductive technology (ART) treatment, anti-Mullerian hormone, follicle-stimulating hormone, or antral follicle count in the fresh cycle (P>0.05). The ERA test identified 35% of samples as receptive and 65% as nonreceptive, and comparable pregnancy outcomes were observed between receptive and nonreceptive patients (P>0.05). Higher pregnancy and implantation rates were found in the ERA group than in the FET group (P<0.01), while no significant differences were detected between the 2 groups in terms of miscarriage rates (P>0.05). CONCLUSIONS In this study of Chinese women with RIF undergoing in vitro fertilization and embryo transfer, ERA-guided pET resulted in a significant improvement in pregnancy and implantation rates when compared with FET.

Effectiveness comparison between endometrial receptivity array, immune profiling and the combination in treating patients with multiple implantation failure.

PROBLEM: The clinical value of endometrial receptivity array (ERA), endometrial immune profiling, or a combination of both for multiple implantation failure patients is unclear. METHOD OF STUDY: One hundred and seventy-two women with a history of at least two or more consecutive implantation failures in IVF/ICSI treatment were included. According to patients' willingness, they were divided into four groups, 'no treatment', 'Immune Profiling', 'ERA' and 'ERA + Immune Profiling'. Endometrial biopsy was examined by ERA, immune profiling alone, or combination, and intention was adopted accordingly. Pregnancy outcomes were compared, and the association between ERA phases and endometrial immune profiling was also assessed. RESULTS: The overall incidence rate of the displaced window of implantation (WOI) and endometrial immune dysregulations were 84.9% and 75.3%, respectively. Implantation rate was significantly higher in the 'ERA + Immune Profiling' group than the 'no treatment' group (P = .007). Clinical pregnancy rate was somewhat improved in the three treatment groups but with a borderline significance (P = .071). After controlling for other confounders, 'ERA + Immune Profiling' treatment was associated with a higher pregnancy rate [aOR (95%CI)  = â€Š3.412 (1.387-8.395), P = .008]. There was no association between endometrial immune profiling and ERA phases. CONCLUSIONS: Our findings highlight the high incidence of displaced WOI and endometrial immune dysregulation in multiple implantation failure patients. The combination of ERA and endometrial immune profiling is more likely to have clinical value than ERA or immune profiling alone. These data suggested the unsubstitutability of ERA and endometrial immune profiling on the treatment outcome for multiple implantation failure patients.