Risk prediction model based on machine learning for predicting miscarriage among pregnant patients with immune abnormalities.

Introduction: It is known that patients with immune-abnormal co-pregnancies are at a higher risk of adverse pregnancy outcomes. Traditional pregnancy risk management systems have poor prediction abilities for adverse pregnancy outcomes in such patients, with many limitations in clinical application. In this study, we will use machine learning to screen high-risk factors for miscarriage and develop a miscarriage risk prediction model for patients with immune-abnormal pregnancies. This model aims to provide an adjunctive tool for the clinical identification of patients at high risk of miscarriage and to allow for active intervention to reduce adverse pregnancy outcomes. Methods: Patients with immune-abnormal pregnancies attending Sichuan Provincial People's Hospital were collected through electronic medical records (EMR). The data were divided into a training set and a test set in an 8:2 ratio. Comparisons were made to evaluate the performance of traditional pregnancy risk assessment tools for clinical applications. This analysis involved assessing the cost-benefit of clinical treatment, evaluating the model's performance, and determining its economic value. Data sampling methods, feature screening, and machine learning algorithms were utilized to develop predictive models. These models were internally validated using 10-fold cross-validation for the training set and externally validated using bootstrapping for the test set. Model performance was assessed by the area under the characteristic curve (AUC). Based on the best parameters, a predictive model for miscarriage risk was developed, and the SHapley additive expansion (SHAP) method was used to assess the best model feature contribution. Results: A total of 565 patients were included in this study on machine learning-based models for predicting the risk of miscarriage in patients with immune-abnormal pregnancies. Twenty-eight risk warning models were developed, and the predictive model constructed using XGBoost demonstrated the best performance with an AUC of 0.9209. The SHAP analysis of the best model highlighted the total number of medications, as well as the use of aspirin and low molecular weight heparin, as significant influencing factors. The implementation of the pregnancy risk scoring rules resulted in accuracy, precision, and F1 scores of 0.3009, 0.1663, and 0.2852, respectively. The economic evaluation showed a saving of ¥7,485,865.7 due to the model. Conclusion: The predictive model developed in this study performed well in estimating the risk of miscarriage in patients with immune-abnormal pregnancies. The findings of the model interpretation identified the total number of medications and the use of other medications during pregnancy as key factors in the early warning model for miscarriage risk. This provides an important basis for early risk assessment and intervention in immune-abnormal pregnancies. The predictive model developed in this study demonstrated better risk prediction performance than the Pregnancy Risk Management System (PRMS) and also demonstrated economic value. Therefore, miscarriage risk prediction in patients with immune-abnormal pregnancies may be the most cost-effective management method.

Prophylactic use of an infrarenal abdominal aorta balloon catheter in pregnancies complicated by placenta accreta.

This study evaluated the surgical and neonatal outcomes of 71 patients diagnosed with placenta accreta before caesarean section with or without placement of a prophylactic abdominal aorta balloon catheter. This study took place at our hospital from January 2013 to May 2015. Thirty patients had a prophylactic balloon catheter inserted (balloon group), and 41 patients did not receive the intervention (control group). The mean estimated blood loss and decrease in haemoglobin after surgery was significantly lower in the balloon group than in the control group. No significant difference was found in duration of operation, transfusion, or percentage requirement of caesarean hysterectomy. The incidence of catheterisation-related complications was 3.3%. One patient had pain in her right leg, caused by an ultrasound-confirmed haematoma in the front wall of the right common femoral artery. No significant difference was found in the rate of surgery-related complications and neonatal outcomes between the groups. Prophylactic placement of an infrarenal abdominal aorta balloon catheter in patients with placenta accreta can effectively reduce intraoperative haemorrhage, without causing any obvious adverse maternal or neonatal outcomes. Impact statement Prophylactic placement of endovascular balloon catheters for controlling intraoperative haemorrhage in women with placenta accreta has been a topic of debate for nearly 2 decades. The most common type of occlusion is internal iliac artery balloon occlusion, only a few studies have focused on intraoperative aortic balloon occlusion This retrospective case-control study included relatively large number of cases and the result shown this technique can effectively reduce intraoperative haemorrhage in patients with placenta accreta, without causing any obvious adverse maternal or neonatal outcomes. It provides another safe and effective method for intraoperative haemorrhage control and even uterine preservation.

Estradiol promotes cells invasion by activating ß-catenin signaling pathway in endometriosis.

Endometriosis is an estrogen-dependent disease that involves the adhesion, invasion, and angiogenesis of endometrial tissues outside of the uterine cavity. We hypothesized that a link exists between estrogen and beta-catenin (ß-catenin) signaling in the pathogenesis of endometriosis. Human endometrial stromal cells (HESCs) were separated from eutopic endometrial tissues that were obtained from patients with endometriosis. ß-catenin expression and cells invasiveness ability were up-regulated by 17ß-estradiol (E2) in an estrogen receptor (ESR)-dependent manner, whereas ß-catenin siRNA abrogated this phenomenon. Moreover, co-immunoprecipitation and dual immunofluorescence studies confirmed ESR1, ß-catenin, and lymphoid enhancer factor 1/T cell factor 3 co-localization in the nucleus in HESCs after E2 treatment. To determine the role of ß-catenin signaling in the implantation of ectopic endometrium, we xenotransplanted eutopic endometrium from endometriosis patients into ovariectomized severe combined immunodeficiency mice. The implantation of the endometrium was suppressed by ß-catenin siRNA. Collectively, studies regarding ß-catenin signaling are critical for improving our understanding of the pathogenesis of estrogen-induced endometriosis, which can translate into the development of treatments and therapeutic strategies for endometriosis.

Cardiovascular medications in angiogenesis--how to avoid the sting in the tail.

Cancer and cardiovascular disease are the leading causes of death worldwide. Cardiovascular medications have recently been found to have favorable effects also for the treatment of noncardiovascular diseases, including cancer. In this review, we use a reverse bedside-to-bench approach to investigate the effects of common cardiovascular medications on tumor angiogenesis and vascular angiogenesis. Aspirin seems to reduce the risk of developing cancer, particularly colon cancer. However, whether the protective influence of aspirin is due to antiangiogenesis effect is still unclear. ß-Blockers, which are normally used to reduce heart rate and prolong diastole, trigger an increase in stretch-associated release of proangiogenic growth factors thereby inducing angiogenesis. However, according to other studies ß-blockers are able to inhibit angiogenesis via multiplicate mechanisms. Similarly, angiotensin converting enzyme inhibitor and angiotensin II type 1 receptor blocker have controversial effects for the regulation of cell proliferation and angiogenesis. Statins can augment collateral vascular growth in ischemic tissues and restrict the development of cancer. So this topical anti-inflammatory drug seems to be of high value for further therapy. Finally, suggestions on how this pilot experience may guide the conduct of future preclinical investigations, and clinical trials are discussed.

Acupuncture on the Endometrial Morphology, the Serum Estradiol and Progesterone Levels, and the Expression of Endometrial Leukaemia-inhibitor Factor and Osteopontin in Rats.

Although it is well known that acupuncture has beneficial effects on a variety of medical conditions especially in pain relief, nausea, and vomiting, it remains controversial whether it has positive impact on the female reproduction. The present study aimed to evaluate whether the following endometrial receptivity factors: the endometrial morphology, the hormone concentrations, and the protein expression of endometrial leukaemia-inhibitory factor (LIF) and osteopontin (OPN) could be improved by the acupuncture in clomiphene citrate(CC)-induced rat model during implantation period. Results showed that, compared with the CC group, glandular development advanced, the serum estradiol levels decreased significantly, and the glandular area and endometrial LIF and OPN expression were significantly higher in acupuncture group. There were no significant differences in serum progesterone levels, endometrial thickness, and stromal area between groups. These results suggest that acupuncture can improve certain aspects of endometrial receptivity in CC-induced rat model during implantation period, which might result in endometrial state better to female reproduction.