Machine learning applied in maternal and fetal health: a narrative review focused on pregnancy diseases and complications

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.

Berberis microphylla G. Forst Intake Reduces the Cardiovascular Disease Plasmatic Markers Associated with a High-Fat Diet in a Mice Model

Polyphenols are bioactive substances that participate in the prevention of chronic illnesses. High content has been described in Berberis microphylla G. Forst (calafate), a wild berry extensively distributed in Chilean-Argentine Patagonia. We evaluated its beneficial effect through the study of mouse plasma metabolome changes after chronic consumption of this fruit. Characterized calafate extract was administered in water, for four months, to a group of mice fed with a high-fat diet and compared with a control diet. Metabolome changes were studied using UHPLC-DAD-QTOF-based untargeted metabolomics. The study was complemented by the analysis of protein biomarkers determined using Luminex technology, and quantification of OH radicals by electron paramagnetic resonance spectroscopy. Thirteen features were identified with a maximum annotation level-A, revealing an increase in succinic acid, activation of tricarboxylic acid and reduction of carnitine accumulation. Changes in plasma biomarkers were related to inflammation and cardiovascular disease, with changes in thrombomodulin (-24%), adiponectin (+68%), sE-selectin (-34%), sICAM-1 (-24%) and proMMP-9 (-31%) levels. The production of OH radicals in plasma was reduced after calafate intake (-17%), especially for the group fed with a high-fat diet. These changes could be associated with protection against atherosclerosis due to calafate consumption, which is discussed from a holistic and integrative point of view.

Pathophysiological Role of Genetic Factors Associated With Gestational Diabetes Mellitus

Gestational Diabetes Mellitus (GDM) is a highly prevalent maternal pathology characterized by maternal glucose intolerance during pregnancy that is, associated with severe complications for both mother and offspring. Several risk factors have been related to GDM; one of the most important among them is genetic predisposition. Numerous single nucleotide polymorphisms (SNPs) in genes that act at different levels on various tissues, could cause changes in the expression levels and activity of proteins, which result in glucose and insulin metabolism dysfunction. In this review, we describe various SNPs; which according to literature, increase the risk of developing GDM. These SNPs include: (1) those associated with transcription factors that regulate insulin production and excretion, such as rs7903146 (TCF7L2) and rs5015480 (HHEX); (2) others that cause a decrease in protective hormones against insulin resistance such as rs2241766 (ADIPOQ) and rs6257 (SHBG); (3) SNPs that cause modifications in membrane proteins, generating dysfunction in insulin signaling or cell transport in the case of rs5443 (GNB3) and rs2237892 (KCNQ1); (4) those associated with enzymes such as rs225014 (DIO2) and rs9939609 (FTO) which cause an impaired metabolism, resulting in an insulin resistance state; and (5) other polymorphisms, those are associated with growth factors such as rs2146323 (VEGFA) and rs755622 (MIF) which could cause changes in the expression levels of these proteins, producing endothelial dysfunction and an increase of pro-inflammatory cytokines, characteristic on GDM. While the pathophysiological mechanism is unclear, this review describes various potential effects of these polymorphisms on the predisposition to develop GDM.

Increased P2×2 receptors induced by amyloid-β peptide participates in the neurotoxicity in alzheimer's disease

Amyloid beta peptide (Aβ) is tightly associated with the physiopathology of Alzheimer's Disease (AD) as one of the most important factors in the evolution of the pathology. In this context, we previously reported that Aβ increases the expression of ionotropic purinergic receptor 2 (P2×2R). However, its role on the cellular and molecular Aβ toxicity is unknown, especially in human brain of AD patients. Using cellular and molecular approaches in hippocampal neurons, PC12 cells, and human brain samples of patients with AD, we evaluated the participation of P2×2R in the physiopathology of AD. Here, we reported that Aβ oligomers (Aβo) increased P2×2 levels in mice hippocampal neurons, and that this receptor increases at late Braak stages of AD patients. Aβo also increases the colocalization of APP with Rab5, an early endosomes marker, and decreased the nuclear/cytoplasmic ratio of Fe65 and PGC-1α immunoreactivity. The overexpression in PC12 cells of P2×2a, but not P2×2b, replicated these changes in Fe65 and PGC-1α; however, both overexpressed isoforms increased levels of Aβ. Taken together, these data suggest that P2×2 is upregulated in AD and it could be a key potentiator of the physiopathology of Aβ. Our results point to a possible participation in a toxic cycle that increases Aβ production, Ca²⁺ overload, and a decrease of PGC-1α. These novel findings put the P2×2R as a key novel pharmacological target to develop new therapeutic strategies to treat Alzheimer's Disease.

High levels of maternal total tri-iodothyronine, and low levels of fetal free L-thyroxine and total tri-iodothyronine, are associated with altered deiodinase expression and activity in placenta with gestational diabetes mellitus

Gestational Diabetes Mellitus (GDM) is characterized by abnormal maternal D-glucose metabolism and altered insulin signaling. Dysregulation of thyroid hormones (TH) tri-iodethyronine (T3) and L-thyroxine (T4) Hormones had been associated with GDM, but the physiopathological meaning of these alterations is still unclear. Maternal TH cross the placenta through TH Transporters and their Deiodinases metabolize them to regulate fetal TH levels. Currently, the metabolism of TH in placentas with GDM is unknown, and there are no other studies that evaluate the fetal TH from pregnancies with GDM. Therefore, we evaluated the levels of maternal TH during pregnancy, and fetal TH at delivery, and the expression and activity of placental deiodinases from GDM pregnancies. Pregnant women were followed through pregnancy until delivery. We collected blood samples during 10-14, 24-28, and 36-40 weeks of gestation for measure Thyroid-stimulating hormone (TSH), Free T4 (FT4), Total T4 (TT4), and Total T3 (TT3) concentrations from Normal Glucose Tolerance (NGT) and GDM mothers. Moreover, we measure fetal TSH, FT4, TT4, and TT3 in total blood cord at the delivery. Also, we measured the placental expression of Deiodinases by RT-PCR, western-blotting, and immunohistochemistry. The activity of Deiodinases was estimated quantified rT3 and T3 using T4 as a substrate. Mothers with GDM showed higher levels of TT3 during all pregnancy, and an increased in TSH during second and third trimester, while lower concentrations of neonatal TT4, FT4, and TT3; and an increased TSH level in umbilical cord blood from GDM. Placentae from GDM mothers have a higher expression and activity of Deiodinase 3, but lower Deiodinase 2, than NGT mothers. In conclusion, GDM favors high levels of TT3 during all gestation in the mother, low levels in TT4, FT4 and TT3 at the delivery in neonates, and increases deiodinase 3, but reduce deiodinase 2 expression and activity in the placenta.

Maternal thyroid profile in first and second trimester of pregnancy is correlated with gestational diabetes mellitus through machine learning

There is evidence about a possible relationship between thyroid abnormalities and gestational diabetes mellitus (GDM). However, there is still no conclusive data on this dependence, since no strong correlation has been proved. In this work, we used machine learning to determine whether there is a correlation between maternal thyroid profile in first and second trimester of pregnancy and GDM. Using principal component analysis, it was possible to find an evident correlation between both, which could be used as a complement for a more sensitive GDM diagnosis.