Predicting risk of low birth weight offspring from maternal features and blood polycyclic aromatic hydrocarbon concentration

Adverse impact of phthalate and polycyclic aromatic hydrocarbon mixtures on birth outcomes: A metabolome Exposome-Wide association study

It has been well-investigating that individual phthalates (PAEs) or polycyclic aromatic hydrocarbons (PAHs) affect public health. However, there is still a gap that the mixture of PAEs and PAHs impacts birth outcomes. Through innovative methods for mixtures in epidemiology, we used a metabolome Exposome-Wide Association Study (mExWAS) to evaluate and explain the association between exposure to PAEs and PAHs mixtures and birth outcomes. Exposure to a higher level of PAEs and PAHs mixture was associated with lower birth weight (maximum cumulative effect: 143.5 g) rather than gestational age. Mono(2-ethlyhexyl) phthalate (MEHP) (posterior inclusion probability, PIP = 0.51), 9-hydroxyphenanthrene (9-OHPHE) (PIP = 0.53), and 1-hydroxypyrene (1-OHPYR) (PIP = 0.28) were identified as the most important compounds in the mixture. In mExWAS, we successfully annotated four overlapping metabolites associated with both MEHP/9-OHPHE/1-OHPYR and birth weight, including arginine, stearamide, Arg-Gln, and valine. Moreover, several lipid-related metabolism pathways, including fatty acid biosynthesis and degradation, alpha-linolenic acid, and linoleic acid metabolism, were disturbed. In summary, these findings may provide new insights into the underlying mechanisms by which PAE and PAHs affect fetal growth.

Presence of polycyclic aromatic hydrocarbons and persistent organochlorine pollutants in human Milk: Evaluating their levels, association with Total antioxidant capacity, and risk assessment

Breastfeeding provides numerous health benefits for both infants and mothers, promoting optimal growth and development while offering protection against various illnesses and diseases. This study investigated the levels of polychlorinated biphenyls (PCB), organochlorine pesticides (OCP) and polycyclic aromatic hydrocarbons (PAH) in human milk sampled in Zadar (Croatia). The primary objectives were twofold: firstly, to evaluate the individual impact of each compound on the total antioxidant capacity (TAC) value, and secondly, to assess associated health risks. Notably, this study presents pioneering and preliminary insights into PAH levels in Croatian human milk, contributing to the limited research on PAH in breast milk worldwide. PCB and OCP levels in Croatian human milk were found to be relatively lower compared to worldwide data. Conversely, PAH levels were comparatively higher, albeit with lower detection frequencies. A negative correlation was established between organic contaminant levels and antioxidative capacity, suggesting a potential link between higher antioxidative potential and lower organic contaminant levels. Diagnostic ratio pointed towards traffic emissions as the primary source of the detected PAH. The presence of PAH suggests potential health risk, underscoring the need for further in-depth investigation.

Cell type-dependent response to benzo(a)pyrene exposure of human placental cell lines under normoxic, hypoxic, and pro-inflammatory conditions

Benzo(a)pyrene (BaP) can be detected in the human placenta. However, little is known about the effects of BaP exposure on different placental cells under various conditions. In this study, we aimed to investigate the effects of BaP on mitochondrial function, pyrin domain-containing protein 3 (NLRP3) inflammasome, and apoptosis in three human trophoblast cell lines under normoxia, hypoxia, and inflammatory conditions. JEG-3, BeWo, and HTR-8/SVneo cell lines were exposed to BaP under normoxia, hypoxia, or inflammatory conditions for 24 h. After treatment, we evaluated cell viability, apoptosis, aryl hydrocarbon receptor (AhR) protein and cytochrome P450 (CYP) gene expression, mitochondrial function, including mitochondrial DNA copy number (mtDNAcn), mitochondrial membrane potential (ΔΨm), intracellular adenosine triphosphate (iATP), and extracellular ATP (eATP), nitric oxide (NO), NLPR3 inflammasome proteins, and interleukin (IL)-1β. We found that BaP upregulated the expression of AhR or CYP genes to varying degrees in all three cell lines. Exposure to BaP alone increased ΔΨm in all cell lines but decreased NO in BeWo and HTR-8/SVneo, iATP in HTR-8/SVneo, and cell viability in JEG-3, without affecting apoptosis. Under hypoxic conditions, BaP did not increase the expression of AhR and CYP genes in JEG-3 cells but increased CYP gene expression in two others. Pro-inflammatory conditions did not affect the response of the 3 cell lines to BaP with respect to the expression of CYP genes and changes in the mitochondrial function and NLRP3 inflammasome proteins. In addition, in HTR-8/SVneo cells, BaP increased IL-1β secretion in the presence of hypoxia and poly(I:C). In conclusion, our results showed that BaP affected mitochondrial function in trophoblast cell lines by increasing ΔΨm. This increased ΔΨm may have rescued the trophoblast cells from activation of the NLRP3 inflammasome and apoptosis after BaP treatment. We also observed that different human trophoblast cell lines had cell type-dependent responses to BaP exposure under normoxia, hypoxia, or pro-inflammatory conditions.

The association between exposure to polycyclic aromatic hydrocarbons and birth outcomes: A systematic review and meta-analysis of observational studies

Exposure to polycyclic aromatic hydrocarbons (PAHs) has been linked to adverse birth outcomes; however, to date, the available studies on such relations, with the exception of birth weight, has not been systematically synthesized. We conducted a systematic review and meta-analysis of the available observational studies on the association of maternal exposure to PAHs and their metabolites during pregnancy with indicators of fetal growth and gestational age at delivery. We searched Web of Science, PubMed and Scopus systematically for all relevant published papers in English until 13 January 2023. Random effects meta-analysis was applied to synthesize the association estimates. Publication bias was assessed using Egger's regression. A total of 31 articles were included in our review (n = 703,080 participants). Our quality assessment of reviewed papers showed that 19 research had excellent, nine had good, and three had fair quality. Most of the reviewed studies on exposure to PAHs and their metabolites with gestational age and preterm birth (seven studies) reported no statistically significant association. Eight studies were eligible for our meta-analysis. Results of the meta-analysis indicated that higher levels of maternal urinary 1-OHP was associated with lower birth weight, birth length and head circumference and a higher risk of low birth weight (LBW). However, these associations were not statistically significant. Similarly, the combined association between maternal urinary 1-OHP and newborn's Ponderal index (PI) and Cephalization index were not statistically significant. Overall, our systematic review and meta-analysis suggested a potential adverse impact of exposure to PAHs on LBW, HC, and CC; however, further studies are required to be able to draw concrete conclusions on such associations.

Node embedding-based graph autoencoder outlier detection for adverse pregnancy outcomes

Adverse pregnancy outcomes, such as low birth weight (LBW) and preterm birth (PTB), can have serious consequences for both the mother and infant. Early prediction of such outcomes is important for their prevention. Previous studies using traditional machine learning (ML) models for predicting PTB and LBW have encountered two important limitations: extreme class imbalance in medical datasets and the inability to account for complex relational structures between entities. To address these limitations, we propose a node embedding-based graph outlier detection algorithm to predict adverse pregnancy outcomes. We developed a knowledge graph using a well-curated representative dataset of the Emirati population and two node embedding algorithms. The graph autoencoder (GAE) was trained by applying a combination of original risk factors and node embedding features. Samples that were difficult to reconstruct at the output of GAE were identified as outliers considered representing PTB and LBW samples. Our experiments using LBW, PTB, and very PTB datasets demonstrated that incorporating node embedding considerably improved performance, achieving a 12% higher AUC-ROC compared to traditional GAE. Our study demonstrates the effectiveness of node embedding and graph outlier detection in improving the prediction performance of adverse pregnancy outcomes in well-curated population datasets.

Building a predictive model of low birth weight in low- and middle-income countries: a prospective cohort study

BACKGROUND

Low birth weight (LBW, < 2500 g) infants are at significant risk for death and disability. Improving outcomes for LBW infants requires access to advanced neonatal care, which is a limited resource in low- and middle-income countries (LMICs). Predictive modeling might be useful in LMICs to identify mothers at high-risk of delivering a LBW infant to facilitate referral to centers capable of treating these infants.

METHODS

We developed predictive models for LBW using the NICHD Global Network for Women's and Children's Health Research Maternal and Newborn Health Registry. This registry enrolled pregnant women from research sites in the Democratic Republic of the Congo, Zambia, Kenya, Guatemala, India (2 sites: Belagavi, Nagpur), Pakistan, and Bangladesh between January 2017 - December 2020. We tested five predictive models: decision tree, random forest, logistic regression, K-nearest neighbor and support vector machine.

RESULTS

We report a rate of LBW of 13.8% among the eight Global Network sites from 2017-2020, with a range of 3.8% (Kenya) and approximately 20% (in each Asian site). Of the five models tested, the logistic regression model performed best with an area under the curve of 0.72, an accuracy of 61% and a recall of 72%. All of the top performing models identified clinical site, maternal weight, hypertensive disorders, severe antepartum hemorrhage and antenatal care as key variables in predicting LBW.

CONCLUSIONS

Predictive modeling can identify women at high risk for delivering a LBW infant with good sensitivity using clinical variables available prior to delivery in LMICs. Such modeling is the first step in the development of a clinical decision support tool to assist providers in decision-making regarding referral of these women prior to delivery. Consistent referral of women at high-risk for delivering a LBW infant could have extensive public health consequences in LMICs by directing limited resources for advanced neonatal care to the infants at highest risk.

Effects of polycyclic aromatic hydrocarbons (PAHs) on pregnancy, placenta, and placental trophoblasts

Polycyclic aromatic hydrocarbons (PAHs) are a group of persistent organic pollutants that are carcinogenic, mutagenic, endocrine-toxic, and immunotoxic. PAHs can be found in maternal and fetal blood and in the placenta during pregnancy. They may thus affect placental and fetal development. Therefore, the exposure levels and toxic effects of PAHs in the placenta deserve further study and discussion. This review aims to summarize current knowledge on the effects of PAHs and their metabolites on pregnancy and birth outcomes and on placental trophoblast cells. A growing number of epidemiological studies detected PAH-DNA adducts as well as the 16 high-priority PAHs in the human placenta and showed that placental PAH exposure is associated with adverse fetal outcomes. Trophoblasts are important cells in the placenta and are involved in placental development and function. In vitro studies have shown that exposure to either PAH mixtures, benzo(a)pyrene (BaP) or BaP metabolite benzo(a)pyrene-7,8-dihydrodiol-9,10-epoxide (BPDE) affected trophoblast cell viability, differentiation, migration, and invasion through various signaling pathways. Furthermore, similar effects of BPDE on trophoblast cells could also be observed in BaP-treated mouse models and were related to miscarriage. Although the current data show that PAHs may affect placental trophoblast cells and pregnancy outcomes, further studies (population studies, in vitro studies, and animal studies) are necessary to show the specific effects of different PAHs on placental trophoblasts and pregnancy outcomes.

A Machine Learning-Based Intrauterine Growth Restriction (IUGR) Prediction Model for Newborns

Intrauterine growth restriction (IUGR) is a condition in which the fetal weight is below the 10th percentile for its gestational age. Prenatal exposure to metals can cause a decrease in fetal growth during gestation thereby reducing birth weight. Therefore, the aim of the present study was to develop a machine learning model for early prediction of IUGR. A total of 126 IUGR and 88 appropriate-for-gestational-age (AGA) samples were collected from the Gynecology Department, Safdarjung Hospital, New Delhi. The predictive models were developed using the Weka software. The models developed using all the features gave the highest accuracy of 95.5% with support vector machine (SMO) algorithm and 88.5% with multilayer perceptron (MLP) algorithm. Further, models developed after feature selection using 14 important and statistically significant variables also gave the highest accuracy of 98.5% with SMO algorithm and 99% with Naïve Bayes (NB) algorithm. The study concluded SMO_31, SMO_14, MLP_31, and NB_14 to be the better classifiers for IUGR prediction.

In-silico study of reducing human health risk of POP residues' direct (from tea) or indirect exposure (from tea garden soil): Improved rhizosphere microbial degradation, toxicity control, and mechanism analysis

The accumulation of potentially harmful substances in tea garden soils and tea leaves, especially persistent organic pollutants (POPs), is a special concern for tea consumers worldwide. However, their potential health and ecological risks in tea gardens have rarely been investigated. This study proposed measures to improve the degradation ability of POPs by the tea rhizosphere and to reduce the human health risks caused by POPs after tea consumption. In this study, the binding energy values of six types of POPs and the degraded protein were used to reflect the degradation ability and calculated using molecular dynamic simulations. The main root secretions (i.e., catechin, glucose, arginine, and oxalic acid) were selected and applied with a combination of tea fertilizer and trace element combination (i.e., urea, straw, and copper element), leading to an improved degradation ability (49.59 %) of POPs. To investigate the mechanisms of the factors that affect the degradation ability, molecular docking, tensor singular value decomposition methods, multivariate correlation analysis and 2D-QSAR model were used. The results showed that the solvation energy and solvent accessible surface area are the main forces, and the molecular weight, boiling point, and topological radius of the POPs were the key molecular features affecting their degradation ability. Based on the three key characteristics, a diet avoidance scheme (i.e., avoiding lysine, maslinic acid, ethanol, perfluorocaproic acid, and cholesterol with tea), which can reduce the binding ability of POP residues to aromatic hydrocarbon receptors by 506.13 %. This work will provide theoretical strategies to improve the quality and safety of tea production and reduce the potential risks of harmful substance residues in tea garden soils and tea leaves.

Infant birth weight estimation and low birth weight classification in United Arab Emirates using machine learning algorithms

Accurate prediction of a newborn’s birth weight (BW) is a crucial determinant to evaluate the newborn’s health and safety. Infants with low BW (LBW) are at a higher risk of serious short- and long-term health outcomes. Over the past decade, machine learning (ML) techniques have shown a successful breakthrough in the field of medical diagnostics. Various automated systems have been proposed that use maternal features for LBW prediction. However, each proposed system uses different maternal features for LBW classification and estimation. Therefore, this paper provides a detailed setup for BW estimation and LBW classification. Multiple subsets of features were combined to perform predictions with and without feature selection techniques. Furthermore, the synthetic minority oversampling technique was employed to oversample the minority class. The performance of 30 ML algorithms was evaluated for both infant BW estimation and LBW classification. Experiments were performed on a self-created dataset with 88 features. The dataset was obtained from 821 women from three hospitals in the United Arab Emirates. Different performance metrics, such as mean absolute error and mean absolute percent error, were used for BW estimation. Accuracy, precision, recall, F-scores, and confusion matrices were used for LBW classification. Extensive experiments performed using five-folds cross validation show that the best weight estimation was obtained using Random Forest algorithm with mean absolute error of 294.53 g while the best classification performance was obtained using Logistic Regression with SMOTE oversampling techniques that achieved accuracy, precision, recall and F1 score of 90.24%, 87.6%, 90.2% and 0.89, respectively. The results also suggest that features such as diabetes, hypertension, and gestational age, play a vital role in LBW classification.

Chronic Kidney Disease and Gut Microbiota: What Is Their Connection in Early Life?

The gut–kidney interaction implicating chronic kidney disease (CKD) has been the focus of increasing interest in recent years. Gut microbiota-targeted therapies could prevent CKD and its comorbidities. Considering that CKD can originate in early life, its treatment and prevention should start in childhood or even earlier in fetal life. Therefore, a better understanding of how the early-life gut microbiome impacts CKD in later life and how to develop ideal early interventions are unmet needs to reduce CKD. The purpose of the current review is to summarize (1) the current evidence on the gut microbiota dysbiosis implicated in pediatric CKD; (2) current knowledge supporting the impact of the gut–kidney axis in CKD, including inflammation, immune response, alterations of microbiota compositions, short-chain fatty acids, and uremic toxins; and (3) an overview of the studies documenting early gut microbiota-targeted interventions in animal models of CKD of developmental origins. Treatment options include prebiotics, probiotics, postbiotics, etc. To accelerate the transition of gut microbiota-based therapies for early prevention of CKD, an extended comprehension of gut microbiota dysbiosis implicated in renal programming is needed, as well as a greater focus on pediatric CKD for further clinical translation.

Maternal exposure to ambient PM2.5 and term birth weight: A systematic review and meta-analysis of effect estimates

Effect estimates of prenatal exposure to ambient PM_2.5 on change in grams (β) of birth weight among term births (≥37 weeks of gestation; term birth weight, TBW) vary widely across studies. We present the first systematic review and meta-analysis of evidence regarding these associations. Sixty-two studies met the eligibility criteria for this review, and 31 studies were included in the meta-analysis. Random-effects meta-analysis was used to assess the quantitative relationships. Subgroup analyses were performed to gain insight into heterogeneity derived from exposure assessment methods (grouped by land use regression [LUR]-models, aerosol optical depth [AOD]-based models, interpolation/dispersion/Bayesian models, and data from monitoring stations), study regions, and concentrations of PM_2.5 exposure. The overall pooled estimate involving 23,925,941 newborns showed that TBW was negatively associated with PM_2.5 exposure (per 10 μg/m³ increment) during the entire pregnancy (β = -16.54 g), but with high heterogeneity (I² = 95.6%). The effect estimate in the LUR-models subgroup (β = -16.77 g) was the closest to the overall estimate and with less heterogeneity (I² = 18.3%) than in the other subgroups of AOD-based models (β = -41.58 g; I² = 95.6%), interpolation/dispersion models (β = -10.78 g; I² = 86.6%), and data from monitoring stations (β = -11.53 g; I² = 97.3%). Even PM_2.5 exposure levels of lower than 10 μg/m³ (the WHO air quality guideline value) had adverse effects on TBW. The LUR-models subgroup was the only subgroup that obtained similar significant of negative associations during the three trimesters as the overall trimester-specific analyses. In conclusion, TBW was negatively associated with maternal PM_2.5 exposures during the entire pregnancy and each trimester. More studies based on relatively standardized exposure assessment methods need to be conducted to further understand the precise susceptible exposure time windows and potential mechanisms.

Interpretable machine learning to identify important predictors of birth weight: A prospective cohort study

BACKGROUND

Predicting birth weight and identifying its risk factors are clinically important. This study aims to use interpretable machine learning to predict birth weight and identity important predictors.

METHODS

This prospective cohort study was conducted in Tongzhou Maternal and Child Health Care Hospital of Beijing, China, recruiting pregnant women between June 2018 and February 2019. We used 24 features to predict infant birth weight, including gestational age, mother's age, parity, history of macrosomia delivery, pre-pregnancy body mass index (BMI), height, father's BMI, lifestyle (diet, physical activity, smoking), and biomarker (fasting glucose and lipids) features. Study outcome was birth weight of infant. We used 8 supervised learning models including 4 individual [linear regression, ridge regression, lasso regression, support vector machines regression (SVR)], and 4 ensemble estimators (random forest, AdaBoost, gradient boosted trees, and voting ensemble for regression) to predict birth weight. Model accuracy was measured by root mean squared error (RMSE) of 10-fold cross validation on the training set and RMSE of prediction on the test set. We used permutation importance algorithm to understand the prediction from the models and what affected them.

RESULT

This study included 4,754 mother-child dyads. RMSEs were lower in voting ensemble for regression, linear regression, and SVR than random forest, AdaBoost, and gradient boosted tree. The 5 most important predictors for infant birth weight were gestational age, fetal sex, preterm birth, mother's height, and pre-pregnancy BMI. After adding ultrasound-measured indicators of fetal growth into predictors, mother's height and pre-pregnancy BMI remained the most important predictors in predicting the outcome.

CONCLUSION

Mother's height and pre-pregnancy BMI were identified as important predictors for infant birth weight. Interpretable machine learning is a promising tool in the prediction of birth weight.

Prenatal exposure to polycyclic aromatic hydrocarbons and effects on neonatal anthropometric indices and thyroid-stimulating hormone in a Middle Eastern population

Prenatal exposure to polycyclic aromatic hydrocarbons (PAHs) evokes extensive concerns regarding public health. Monitoring the pregnant women's exposure can be considered a suitable alternative to assess the fetus's exposure. This study aimed to monitor pregnant women's exposure (n = 126) to PAHs using a biomonitoring approach to evaluate effects on anthropometric indices and neonatal thyroid-stimulating hormone (TSH) in Shiraz, Iran. PAHs priority compounds were measured by gas chromatography-mass spectrometry (GC-MS) after separating blood serum and liquid-liquid extraction (LLE) method. Information on anthropometric indices, neonatal TSH levels, and data from the respondents was obtained from medical records and questionnaires. The mean PAHs concentrations ranged from 0.29 to 327.91 ng/g lipid. There was no significant difference between the measured PAHs in maternal serum at the seventh month and pregnancy termination except for ACY (p-Value<0.05). Regression analysis results showed a significant correlation (p-value<0.05) between exposure to passive smoke and total PAHs concentrations. There was no significant relationship between exposure to PAHs and weight, height, head circumference, and Apgar score of newborns. The results showed TSH decreased by 0.99 units as ACE increased per unit (β = -0.001). This study is the first to evaluate relationships between prenatal exposure to PAHs and effects on newborn health indicators, including TSH levels in a Middle Eastern population. Future studies are suggested to perform detailed assessments of PAHs intake sources, especially in vulnerable populations such as pregnant women and children.

Prenatal exposure to polycyclic aromatic hydrocarbons could increase the risk of low birth weight by affecting the DNA methylation states in a Chinese cohort

Polycyclic aromatic hydrocarbons (PAHs), as a kind of endocrine disruptors, can enter the fetus body cross the placental barrier from prenatal PAHs exposure to cause adverse birth outcomes. However, it is controversial association between prenatal PAHs exposure and low birth weight (LBW) of their infants. So the present study aimed to estimate the effects of prenatal PAHs exposure during the pregnancy on the risk of LBW in a Chinese cohort through modifying the DNA methylation states. A longitudinal prospective study with 407 pregnant women was established from May to October 2019. The prenatal PAHs exposure during the pregnancy was assessed using the internal dose such as the PAHs metabolites and PAH-DNA adducts in the umbilical cord blood. The methylation levels of genomic DNA and growth-related genes (IGF1 and IGF2) were assessed, while the expressions of these genes were both determined by RT-PCR and Elisa methods. The growth outcomes and relevant Z-scores were recorded at birth. The correlations between the DNA methylation status and concentrations of PAHs, expression levels of growth-related genes and body weight/WAZ were investigated as the measures. According to the PAH-DNA adducts, the subjects were divided into two groups: PAHs-exposed group (PAH-DNA adducts>0, n = 55) and non-exposed group (PAH-DNA adducts = 0, n = 352). Compared with the non-exposed group, it displayed marked decreased birth weight, and increased concentrations of PAHs and DNA methylation levels of the global genomic, IGF1 and IGF2 with their lower expressions in the PAHs-exposed group. These hypermethylation (global genomic, CpG14 and CpG15 of IGF1, and CpG14 of IGF2) were positively correlated with the contents of PAHs in the umbilical cord blood, and negatively correlated with the growth outcomes and their expressions. Totally, prenatal PAHs exposures may contribute to an increased risk of LBW of their infants by modulating the DNA methylation states of genomic DNA and growth-related genes (IGF1 and IGF2) in the umbilical cord blood, which could provide the prenatal prevention of PAHs exposure from possible environmental media except from the occupation and tobacco usage to ensure the health of their infants.

Adverse Impact of Environmental Chemicals on Developmental Origins of Kidney Disease and Hypertension

Chronic kidney disease (CKD) and hypertension are becoming a global health challenge, despite developments in pharmacotherapy. Both diseases can begin in early life by so-called "developmental origins of health and disease" (DOHaD). Environmental chemical exposure during pregnancy can affect kidney development, resulting in renal programming. Here, we focus on environmental chemicals that pregnant mothers are likely to be exposed, including dioxins, bisphenol A (BPA), phthalates, per- and polyfluoroalkyl substances (PFAS), polycyclic aromatic hydrocarbons (PAH), heavy metals, and air pollution. We summarize current human evidence and animal models that supports the link between prenatal exposure to environmental chemicals and developmental origins of kidney disease and hypertension, with an emphasis on common mechanisms. These include oxidative stress, renin-angiotensin system, reduced nephron numbers, and aryl hydrocarbon receptor signaling pathway. Urgent action is required to identify toxic chemicals in the environment, avoid harmful chemicals exposure during pregnancy and lactation, and continue to discover other potentially harmful chemicals. Innovation is also needed to identify kidney disease and hypertension in the earliest stage, as well as translating effective reprogramming interventions from animal studies into clinical practice. Toward DOHaD approach, prohibiting toxic chemical exposure and better understanding of underlying mechanisms, we have the potential to reduce global burden of kidney disease and hypertension.

The First Thousand Days: Kidney Health and Beyond

The global burden of chronic kidney disease (CKD) is rising. A superior strategy to advance global kidney health is required to prevent and treat CKD early. Kidney development can be impacted during the first 1000 days of life by numerous factors, including malnutrition, maternal illness, exposure to chemicals, substance abuse, medication use, infection, and exogenous stress. In the current review, we summarize environmental risk factors reported thus far in clinical and experimental studies relating to the programming of kidney disease, and systematize the knowledge on common mechanisms underlying renal programming. The aim of this review is to discuss the primary and secondary prevention actions for enhancing kidney health from pregnancy to age 2. The final task is to address the potential interventions to target renal programming through updating animal studies. Together, we can enhance the future of global kidney health in the first 1000 days of life.

Machine Learning Assisted Prediction of Prognostic Biomarkers Associated With COVID-19, Using Clinical and Proteomics Data

With the availability of COVID-19-related clinical data, healthcare researchers can now explore the potential of computational technologies such as artificial intelligence (AI) and machine learning (ML) to discover biomarkers for accurate detection, early diagnosis, and prognosis for the management of COVID-19. However, the identification of biomarkers associated with survival and deaths remains a major challenge for early prognosis. In the present study, we have evaluated and developed AI-based prediction algorithms for predicting a COVID-19 patient's survival or death based on a publicly available dataset consisting of clinical parameters and protein profile data of hospital-admitted COVID-19 patients. The best classification model based on clinical parameters achieved a maximum accuracy of 89.47% for predicting survival or death of COVID-19 patients, with a sensitivity and specificity of 85.71 and 92.45%, respectively. The classification model based on normalized protein expression values of 45 proteins achieved a maximum accuracy of 89.01% for predicting the survival or death, with a sensitivity and specificity of 92.68 and 86%, respectively. Interestingly, we identified 9 clinical and 45 protein-based putative biomarkers associated with the survival/death of COVID-19 patients. Based on our findings, few clinical features and proteins correlate significantly with the literature and reaffirm their role in the COVID-19 disease progression at the molecular level. The machine learning-based models developed in the present study have the potential to predict the survival chances of COVID-19 positive patients in the early stages of the disease or at the time of hospitalization. However, this has to be verified on a larger cohort of patients before it can be put to actual clinical practice. We have also developed a webserver CovidPrognosis, where clinical information can be uploaded to predict the survival chances of a COVID-19 patient. The webserver is available at http://14.139.62.220/covidprognosis/.

Crude oil and public health issues in Niger Delta, Nigeria: Much ado about the inevitable

The importance of crude oil has come at a great cost. In many developing economies of the world, it can be described as the bitter-sweet crude for its double-edged impacts on the welfare, wellness and wellness of the people. Agitations and restiveness remain characteristic features of Niger Delta following claims of exploitation and neglect of the local population by the multinationals. Literature on the environmental and public health impacts of crude oil was searched from relevant databases such as google scholar, Science Direct, Scopus and PubMed. This paper is a translational scientific and toxicological insight on what should be done by the major players rather than casting unending aspersions. Since living near oil spills and crude oil production sites is an environmental stressor occasioned by exposure to both chemical pollutants and physical menace that are all detrimental to health, cumulative risk assessment CRA is proposed as a viable approach for a comprehensive understanding of the size of this problem. Multinational oil companies should support development of Environmental Medicine Research which will in turn generate data on both how to harness the natural resources to combat the public health issues associated with oil exploration and the mitigation and remediation of the environment. This endeavor will create a waste-to-wealth program that will pacify the restiveness in oil exploring communities. It will be interesting to know that in the same environment that breeds the elephant-in-the-parlor lies the natural antidotes to check-mate the public health malady.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

Background

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

Objective

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians’ decision making.

Methods

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians’ decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ² and I².

Results

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I²=86%; τ²=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I²=75%; τ²=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I²=75%; τ²=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I²=83%; τ²=0.07).

Conclusions

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

Trial Registration

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106