Search

Colposcopy imaging is pivotal in cervical cancer diagnosis, a major health concern for women. The computational challenge lies in accurate lesion recognition. A significant hindrance for many existing machine learning solutions is the scarcity of comprehensive training datasets.

Cervical cancer is the fourth most common female malignancy worldwide. In developing countries, it is the most common subtype of cancer and the third leading cause of cancer mortality among women. Artificial intelligence has the potential to be of real use in the prevention and prompt diagnosis of cervical cancer. The aim of our study was to develop a medical platform consisting of an automated observation sheet containing colposcopy data, a software that would use a machine learning module based on clinical and image data for diagnosis and treatment, and a telemedicine module to enable collaboration between gynecologists.

Background: Normal pregnancy and the postpartum period are characterized by thrombotic predisposition. Consequently, monitoring coagulation markers and conducting risk assessments are essential in preventing thrombotic events that negatively impact both the mother and the child. In medical practice, fibrinogen/fibrin degradation products (FDPs) are the main coagulation markers currently investigated in pregnancy. Methods: We investigated proteins C and S, antiphospholipid antibodies (APLs), human factor V, and beta-2-glycoprotein 1 or apolipoprotein H (APOH) levels to determine whether there is any difference between normal third-trimester pregnancies and pregnant women in late pregnancy who end up developing deep vein thrombosis (DVT). Results: Our data show a significant correlation between protein C levels and the number of weeks of pregnancy, as well as statistically significant differences between healthy pregnant women and pregnant women with DVT in terms of the values of FDP, protein S, and APL. The DVT group had higher FDP levels but lower AFL and protein S values. Conclusions: Given the significant prothrombotic correlation that exists between proteins C and S, we propose that variations in their levels can serve as valuable markers in the evaluation of thrombotic risk during the final stages of pregnancy. [ABSTRACT FROM AUTHOR]

Background and Objectives: Double-J stents are urinary catheters that are frequently used in urology. They are now also used in other specialist areas such as obstetrics and gynecology. However, the use of double-J stents is not without side effects. The aim of this review was to highlight the indications and possible adverse effects of the use of these stents in obstetrics and gynecology. Materials and Methods: We analyzed works published after 1995 in the PUBMED, SCOPUS, and Web of Science databases related to the use of double-J stents in obstetrics and gynecology, as well as reported adverse events. We carried out a narrative review of the available literature on this topic. Results: We identified 69 relevant publications that we included in the review. In obstetrics, indications include the treatment of gestational hydronephrosis, some urological conditions during pregnancy, such as obstructive urinary calculi, with or without superinfection, or intraoperative use for cesarean section or hysterectomy after cesarean section, to protect from, or to solve, ureteral lesions. In gynecology, they are used preoperatively or intraoperatively to protect the ureter during gynecological operations in the pelvic area or postoperatively to repair some ureteral injuries. They are also indicated for ureteral obstructions that occur after pelvic radiotherapy for gynecological neoplasms. Complications associated with the use of double-J stents include more frequent urinary tract infections, lower urinary tract symptoms, calcifications and misplacements. Conclusions: Double-J stents are widely used in obstetrics and gynecology and are characterized by good efficiency and safety, although some side effects may occur (lower urinary tract symptoms, hematuria, complications in birth outcomes), which do not limit their use. Summary of evidence: In this review, we analyzed the indications and complications of double-J ureteral stenting in obstetric and gynecologic patients. We found that the procedure is safe, both in the treatment of ureteral obstruction and in the resolution of postoperative complications. No serious complications of ureteral stenting have been noted that would constitute a contraindication to its use. Future prospective studies in large patient cohorts are necessary to validate our data. [ABSTRACT FROM AUTHOR]

Background/Objectives: Multidrug-resistant urinary tract infections (MDR UTIs) constitute an important public health problem, especially in pregnant patients. The aim of this retrospective study was to characterize the bacterial spectrum and the profile of microbial resistance in cases of UTIs occurring in pregnant women, as well as their impact on obstetrical and neonatal outcomes. Methods: A total of 371 pregnant patients with UTIs were included in the analysis and were segregated into the following groups based on the type of bacterial resistance to antibiotics: MDR UTIs (70 patients, group 1), UTIs resistant to one class of antibiotics (108 patients, group 2), UTIs resistant to two classes of antibiotics (102 patients, group 3), and sensitive UTIs (91 patients, group 4). We used descriptive statistics for characterizing and comparing the microbial spectrum and the clinical characteristics of the patients. A multinomial logistic regression model for evaluating the relationship between the type of urinary tract infection and adverse obstetric or neonatal outcomes was employed. Results: In the case of MDR UTIs, the bacterial spectrum mainly included Escherichia coli, Enterococcus faecalis, and Klebsiella species. We found almost universal resistance to ampicillin. Our data confirmed an increased risk of preterm birth, premature rupture of membranes, neonatal respiratory distress syndrome, and neonatal intensive care unit admission for patients with MDR infections. Conclusions: The increased incidence of pathogens resistant to commonly used antibiotic classes in pregnancy suggests the need for the development of local and national protocols that adapt therapeutic and prophylactic regimens to clinical realities. [ABSTRACT FROM AUTHOR]

More common than cervical cancer, cervical intraepithelial neoplasia (CIN) represents a precursor lesion of cervical carcinoma, being associated with HPV infection. Due to the bidirectional relationship between HPV and estrogen and progesterone in pregnancy, most of the published data claim that precancerous lesions remain stable or even regress during pregnancy, although several studies have indicated the tendency of HSILs to persist. It is considered that pregnancy-related cervical precancerous lesions undergo a postpartum regression, due to stimulatory effects of the immune microenvironment. Due to the rarity of publications on this subject, we aimed to offer a concise overview of and new insights into the current knowledge regarding the pathogenesis, diagnosis, and evolution of pregnancy-associated precancerous lesions, as well as their impact upon gestation and fertility. [ABSTRACT FROM AUTHOR]

(1) Background: Cervical cancer, caused mainly by high-risk Human Papillomavirus (hrHPV), is a significant global health issue. While a Pap smear remains a reliable method for early detection, identifying new biomarkers to stratify the risk is crucial. For this purpose, extensive research has been conducted on detecting DNA methylation. (2) Methods: This cross-sectional study aimed to assess the expression levels of EIF4G3 and SF3B1 in precursor lesions and cervical tumor tissues through qRT-PCR and evaluate the methylation status of their promoters through bisulfite conversion. (3) Results: Both genes showed similar mRNA expression patterns, with the highest levels observed in squamous cell carcinoma (SCC) samples (p < 0.0001). Additionally, methylation analysis indicated increased percentages in the control group for both factors. Notably, the expression levels of both genes were inversely correlated with promoter methylation (EIF4G3—p = 0.0016; SF3B1—p < 0.0001). (4) Conclusions: Regarding the methylation pattern for both genes, we observe a decreasing trend from NILM to SCC patients. Therefore, we concluded that the decrease in methylation at the promoter level for both genes could be an indicator of abnormal cytology. [ABSTRACT FROM AUTHOR]

Aim: The aim of this study is to identify correlations between total antioxidant status values of mothers and their infants and compare these values in accordance to the presence or absence of intrauterine growth restriction.

(1) Background: Trial of labor after cesarean (TOLAC) can be associated with significant maternal and neonatal complications, and the aim of this retrospective study was to calculate the risks and probabilities of these complications in two tertiary maternity centers in Romania. (2) Methods: A total of 216 patients who attempted TOLAC were included in the study and were segregated into two groups, depending on TOLAC success. Medical records were assessed, and clinical data were used to determine the maternal and neonatal risks and complications, using multinomial logistic regression and postestimation predictions. (3) Results: Our data indicated that patients who had a failed TOLAC had significantly higher risks and probabilities of uterine rupture, either complete or incomplete; intensive care unit (ICU) admission; and emergency hysterectomy. The newborns of these mothers had significantly higher risks and probabilities of low Apgar score at birth, neonatal intensive care unit (NICU) admission, and invasive ventilation. (4) Conclusions: Failed TOLAC could lead to significant maternal and neonatal complications, and women who attempt this procedure should be monitored in a tertiary center where a multidisciplinary team and an emergency operating room are available. [ABSTRACT FROM AUTHOR]

(1) Background: The three factors within the Virchow triad play the leading role in the development of deep vein thrombosis (DVT) during pregnancy. (2) Methods: This research approaches the various risk factors associated with DVT and its most representative complications, pulmonary thromboembolism and cerebral venous thrombosis, in pregnant and postpartum women across a 15-year period (2007–2021). (3) Results: A total of 201 out of 287 patients with DVT had associated risk factors, while 86 did not present with any. Out of the 201 patients with risk factors, 47 developed pulmonary thromboembolism, while 12 experienced cerebral thrombosis. The statistical analysis of risk factors involved in DVT revealed high significance for obesity (OR 3.676; CI 2.484–5.439), gestational diabetes (OR 3.394; CI 2.101–5.483), hypertension (OR 2.325; CI 1.591–3.397), preeclampsia (OR 4.753; CI 2.342–9.645), thrombophilia (OR 12.138; CI 8.973–16.417), and varicose veins (OR 9.678; CI 7.321–12.793); for pulmonary thromboembolism, there was high significance for obesity (OR 7.867; CI 4.297–14.401), hypertension (OR 2.605; CI 1.246–5.446), preeclampsia (OR 7.483; CI 2.346–23.872), thrombophilia (OR 11.035; CI 5.910–20.602), and varicose veins (OR 6.837; CI 3.665–12.757); and for cerebral thromboembolism (CTE), the risk factors identified were obesity (OR 6.755; CI 1.954–23.347), hypertension (OR 1.167; CI 0.155–8.770), preeclampsia (OR 9.655; CI 1.283–72.672), and thrombophilia (OR 33.275; CI 12.884–85.939). (4) Conclusions: Obesity was the only significant factor found to influence DVT, pulmonary embolism and CTE risks, and hereditary thrombophilia was the main factor influencing the risk for pulmonary thromboembolism and CTE. Systemic lupus erythematosus and gestational diabetes revealed conflicting results that require further investigation. [ABSTRACT FROM AUTHOR]

Background and Objectives: Polycystic ovary syndrome (PCOS) is a complex disorder that can negatively impact the obstetrical outcomes. The aim of this study was to determine the predictive performance of four machine learning (ML)-based algorithms for the prediction of adverse pregnancy outcomes in pregnant patients diagnosed with PCOS. Materials and Methods: A total of 174 patients equally divided into 2 groups depending on the PCOS diagnosis were included in this prospective study. We used the Mantel–Haenszel test to evaluate the risk of adverse pregnancy outcomes for the PCOS patients and reported the results as a crude and adjusted odds ratio (OR) with a 95% confidence interval (CI). A generalized linear model was used to identify the predictors of adverse pregnancy outcomes in PCOS patients, quantifying their impact as risk ratios (RR) with 95% CIs. Significant predictors were included in four machine learning-based algorithms and a sensitivity analysis was employed to quantify their performance. Results: Our crude estimates suggested that PCOS patients had a higher risk of developing gestational diabetes and had a higher chance of giving birth prematurely or through cesarean section in comparison to patients without PCOS. When adjusting for confounders, only the odds of delivery via cesarean section remained significantly higher for PCOS patients. Obesity was outlined as a significant predictor for gestational diabetes and fetal macrosomia, while a personal history of diabetes demonstrated a significant impact on the occurrence of all evaluated outcomes. Random forest (RF) performed the best when used to predict the occurrence of gestational diabetes (area under the curve, AUC value: 0.782), fetal macrosomia (AUC value: 0.897), and preterm birth (AUC value: 0.901) in PCOS patients. Conclusions: Complex ML algorithms could be used to predict adverse obstetrical outcomes in PCOS patients, but larger datasets should be analyzed for their validation. [ABSTRACT FROM AUTHOR]

(1) Background: Prenatal care providers face a continuous challenge in screening for intrauterine growth restriction (IUGR) and preeclampsia (PE). In this study, we aimed to assess and compare the predictive accuracy of four machine learning algorithms in predicting the occurrence of PE, IUGR, and their associations in a group of singleton pregnancies; (2) Methods: This observational prospective study included 210 singleton pregnancies that underwent first trimester screenings at our institution. We computed the predictive performance of four machine learning-based methods, namely decision tree (DT), naïve Bayes (NB), support vector machine (SVM), and random forest (RF), by incorporating clinical and paraclinical data; (3) Results: The RF algorithm showed superior performance for the prediction of PE (accuracy: 96.3%), IUGR (accuracy: 95.9%), and its subtypes (early onset IUGR, accuracy: 96.2%, and late-onset IUGR, accuracy: 95.2%), as well as their association (accuracy: 95.1%). Both SVM and NB similarly predicted IUGR (accuracy: 95.3%), while SVM outperformed NB (accuracy: 95.8 vs. 94.7%) in predicting PE; (4) Conclusions: The integration of machine learning-based algorithms in the first-trimester screening of PE and IUGR could improve the overall detection rate of these disorders, but this hypothesis should be confirmed in larger cohorts of pregnant patients from various geographical areas. [ABSTRACT FROM AUTHOR]