Introduction: Machine learning (ML) corresponds to a wide variety of methods that use mathematics, statistics and computational science to learn from multiple variables simultaneously. By means of pattern recognition, ML methods are able to find hidden correlations and accomplish accurate predictions regarding different conditions. ML has been successfully used to solve varied problems in different areas of science, such as psychology, economics, biology and chemistry. Therefore, we wondered how far it has penetrated into the field of obstetrics and gynecology.Aim: To describe the state of art regarding the use of ML in the context of pregnancy diseases and complications.Methodology: Publications were searched in PubMed, Web of Science and Google Scholar. Seven subjects of interest were considered: gestational diabetes mellitus, preeclampsia, perinatal death, spontaneous abortion, preterm birth, cesarean section, and fetal malformations.Current state: ML has been widely applied in all the included subjects. Its uses are varied, the most common being the prediction of perinatal disorders. Other ML applications include (but are not restricted to) biomarker discovery, risk estimation, correlation assessment, pharmacological treatment prediction, drug screening, data acquisition and data extraction. Most of the reviewed articles were published in the last five years. The most employed ML methods in the field are non-linear. Except for logistic regression, linear methods are rarely used.Future challenges: To improve data recording, storage and update in medical and research settings from different realities. To develop more accurate and understandable ML models using data from cutting-edge instruments. To carry out validation and impact analysis studies of currently existing high-accuracy ML models.Conclusion: The use of ML in pregnancy diseases and complications is quite recent, and has increased over the last few years. The applications are varied and point not only to the diagnosis, but also to the management, treatment, and pathophysiological understanding of perinatal alterations. Facing the challenges that come with working with different types of data, the handling of increasingly large amounts of information, the development of emerging technologies, and the need of translational studies, it is expected that the use of ML continue growing in the field of obstetrics and gynecology.

OBJECTIVE To determine whether insulin reverses gestational diabetes mellitus (GDM)–reduced expression and activity of human equilibrative nucleoside transporters 1 (hENT1) in human umbilical vein endothelium cells (HUVECs). RESEARCH DESIGN AND METHODS Primary cultured HUVECs from full-term normal (n = 44) and diet-treated GDM (n = 44) pregnancies were used. Insulin effect was assayed on hENT1 expression (protein, mRNA, SLC29A1 promoter activity) and activity (initial rates of adenosine transport) as well as endothelial nitric oxide (NO) synthase activity (serine¹¹⁷⁷ phosphorylation, l-citrulline formation). Adenosine concentration in culture medium and umbilical vein blood (high-performance liquid chromatography) as well as insulin receptor A and B expression (quantitative PCR) were determined. Reactivity of umbilical vein rings to adenosine and insulin was assayed by wire myography. Experiments were in the absence or presence of l-N^G-nitro-l-arginine methyl ester (l-NAME; NO synthase inhibitor) or ZM-241385 (an A_2A-adenosine receptor antagonist). RESULTS Umbilical vein blood adenosine concentration was higher, and the adenosine- and insulin-induced NO/endothelium-dependent umbilical vein relaxation was lower in GDM. Cells from GDM exhibited increased insulin receptor A isoform expression in addition to the reported NO–dependent inhibition of hENT1-adenosine transport and SLC29A1 reporter repression, and increased extracellular concentration of adenosine and NO synthase activity. Insulin reversed all these parameters to values in normal pregnancies, an effect blocked by ZM-241385 and l-NAME. CONCLUSIONS GDM and normal pregnancy HUVEC phenotypes are differentially responsive to insulin, a phenomenon where insulin acts as protecting factor for endothelial dysfunction characteristic of this syndrome. Abnormal adenosine plasma levels, and potentially A_2A-adenosine receptors and insulin receptor A, will play crucial roles in this phenomenon in GDM.

Objective—: Human pregnancy that courses with maternal supraphysiological hypercholesterolemia (MSPH) correlates with atherosclerotic lesions in fetal arteries. It is known that hypercholesterolemia associates with endothelial dysfunction in adults, a phenomenon where nitric oxide (NO) and arginase are involved. However, nothing is reported on potential alterations in the fetoplacental endothelial function in MSPH. The aim of this study was to determine whether MSPH alters fetal vascular reactivity via endothelial arginase/urea and l -arginine transport/NO signaling pathways. Approach and Results—: Total cholesterol <280 mg/dL was considered as maternal physiological hypercholesterolemia (n=46 women) and ≥280 mg/dL as MSPH (n=28 women). Maternal but not fetal total cholesterol and low-density lipoprotein-cholesterol levels were elevated in MSPH. Umbilical veins were used for vascular reactivity assays (wire myography), and primary cultures of umbilical vein endothelial cells to determine arginase, endothelial NO synthase (eNOS), and human cationic amino acid transporter 1 and human cationic amino acid transporter 2A/B expression and activity. MSPH reduced calcitonine gene–related peptide-umbilical vein relaxation and increased intima/media ratio (histochemistry), as well as reduced eNOS activity ( l -citrulline synthesis from l -arginine, eNOS phosphorylation/dephosphorylation), but increased arginase activity and arginase II protein abundance. Arginase inhibition increased eNOS activity and l -arginine transport capacity without altering human cationic amino acid transporter 1 or human cationic amino acid transporter 2A/B protein abundance in maternal physiological hypercholesterolemia and MSPH. Conclusions—: MSPH is a pathophysiological condition altering umbilical vein reactivity because of fetal endothelial dysfunction associated with arginase and eNOS signaling imbalance. We speculate that elevated maternal circulating cholesterol is a factor leading to fetal endothelial dysfunction, which could have serious consequences to the growing fetus.

Gestational diabetes mellitus (GDM) courses with increased fetal plasma adenosine concentration and reduced adenosine transport in placental macrovascular endothelium. Since insulin modulates human equilibrative nucleoside transporters (hENTs) expression/activity, we hypothesize that GDM will alter hENT2-mediated transport in human placental microvascular endothelium (hPMEC), and that insulin will restore GDM to a normal phenotype involving insulin receptors A (IR-A) and B (IR-B). GDM effect on hENTs expression and transport activity, and IR-A/IR-B expression and associated cell signalling cascades (p42/44 mitogen-activated protein kinases (p42/44^mapk) and Akt) role in hPMEC primary cultures was assayed. GDM associates with elevated umbilical whole and vein, but not arteries blood adenosine, and reduced hENTs adenosine transport and expression. IR-A/IR-B mRNA expression and p42/44^mapk/Akt ratios (‘metabolic phenotype’) were lower in GDM. Insulin reversed GDM-reduced hENT2 expression/activity, IR-A/IR-B mRNA expression and p42/44^mapk/Akt ratios to normal pregnancies (‘mitogenic phenotype’). It is suggested that insulin effects required IR-A and IR-B expression leading to differential modulation of signalling pathways restoring GDM-metabolic to a normal-mitogenic like phenotype. Insulin could be acting as protecting factor for placental microvascular endothelial dysfunction in GDM.

Gold nanoparticles (AuNPs) are currently under intense investigation for biomedical and biotechnology applications, thanks to their ease in preparation, stability, biocompatibility, multiple surface functionalities, and size-dependent optical properties. The most commonly used method for AuNP synthesis in aqueous solution is the reduction of tetrachloroauric acid (HAuCl₄) with trisodium citrate. We have observed variations in the pH and in the concentration of the gold colloidal suspension synthesized under standard conditions, verifying a reduction in the reaction yield by around 46% from pH 5.3 (2.4 nM) to pH 4.7 (1.29 nM). Citrate-capped AuNPs were characterized by UV-visible spectroscopy, TEM, EDS, and zeta-potential measurements, revealing a linear correlation between pH and the concentration of the generated AuNPs. This result can be attributed to the adverse effect of protons both on citrate oxidation and on citrate adsorption onto the gold surface, which is required to form the stabilization layer. Overall, this study provides insight into the effect of the pH over the synthesis performance of the method, which would be of particular interest from the point of view of large-scale manufacturing processes.