Detection and prevention of macrosomia

Early Prediction Model of Macrosomia Using Machine Learning for Clinical Decision Support

The condition of fetal overgrowth, also known as macrosomia, can cause serious health complications for both the mother and the infant. It is crucial to identify high-risk macrosomia-relevant pregnancies and intervene appropriately. Despite this need, there are several gaps in research related to macrosomia, including limited predictive models, insufficient machine learning applications, ineffective interventions, and inadequate understanding of how to integrate machine learning models into clinical decision-making. To address these gaps, we developed a machine learning-based model that uses maternal characteristics and medical history to predict macrosomia. Three different algorithms, namely logistic regression, support vector machine, and random forest, were used to develop the model. Based on the evaluation metrics, the logistic regression algorithm provided the best results among the three. The logistic regression algorithm was chosen as the final algorithm to predict macrosomia. The hyper parameters of the logistic regression model were tuned using cross-validation to achieve the best possible performance. Our results indicate that machine learning-based models have the potential to improve macrosomia prediction and enable appropriate interventions for high-risk pregnancies, leading to better health outcomes for both mother and fetus. By leveraging machine learning algorithms and addressing research gaps related to macrosomia, we can potentially reduce the health risks associated with this condition and make informed decisions about high-risk pregnancies.

Correlation between preconception maternal non-occupational exposure to interior decoration or oil paint odour and average birth weight of neonates: findings from a nationwide cohort study in China's rural areas

BACKGROUND

Birth weight is a critical indicator of neonatal health and foretells people's health in adolescence and even adulthood. Some researchers have warned against the adverse effects on babies' birth weight of exposure to pollutants in interior decoration or oil paint by odour intake. This study evaluated the effects of maternal exposure to such factors before conception on the birth weights of neonates.

METHODS

Data on 213 461 cases in this study were from the database of the free National Pre-pregnancy Checkups Project. Defined as 'exposed' were those women exposed to oil paint odour or interior decoration at home or in the workplace within 6 months before their pregnancy. The study focused on revealing the correlation between such exposure and the birth weight of the neonates of these women, especially the incidence of macrosomia and low birth weight (LBW). Statistical analysis was conducted using the Kruskal-Wallis H test, the Mann-Whitney U test and logistic regression.

RESULTS

The birth weight of babies from mothers non-occupationally exposed to such settings averaged 3465 g (range 3150-3650 g), whereas the birth weight of those from mothers free of such exposure averaged 3300 g (range 3000-3600g). Maternal exposure preconception to interior decoration or oil paint odour reduced the incidence of LBW in their babies (p=0.003, OR 0.749, 95% CI 0.617 to 0.909). Such exposure may also augment the probability of macrosomia (p<0.001, OR 1.297, 95% CI 1.133 to 1.484).

CONCLUSION

Maternal exposure to interior decoration or oil paint odour preconception may increase the average birth weight of neonates, as well as the incidence of macrosomia.

Regimens of fetal surveillance of suspected large-for-gestational-age fetuses for improving health outcomes

BACKGROUND

Policies and protocols vary widely for fetal surveillance in a pregnancy where the fetus is suspected to be large-for-gestational-age (LGA). All ultimately culminate in decisions about the mode and timing of birth. LGA is known to be associated with increased risks to both the mother and baby. Interventions based on surveillance regimen findings may be associated with risks to the mother and baby.

OBJECTIVES

To assess the effectiveness or efficacy of different antenatal surveillance methods for the suspected LGA fetus on important health outcomes for the mother and baby.

SEARCH METHODS

We searched the Cochrane Pregnancy and Childbirth Group's Trials Register (30 August 2015), ClinicalTrials.gov and the WHO International Clinical Trials Registry Platform (ICTRP) (21 August 2015).

SELECTION CRITERIA

Published and unpublished randomised, quasi-randomised and cluster-randomised trials comparing the effects of described antenatal fetal surveillance regimens for women with suspected LGA infants.

DATA COLLECTION AND ANALYSIS

We identified no studies that met the inclusion criteria for this review.

MAIN RESULTS

There are no included trials.

AUTHORS' CONCLUSIONS

We found no randomised controlled trials that assessed the effect of antenatal fetal surveillance regimens of a suspected LGA fetus on important health outcomes for the mother and baby.There has been a rise in the prevalence of LGA babies over the past few decades in many countries. Research is therefore required on regimens of antenatal surveillance of suspected LGA infants, in order to guide practice and improve the health outcomes for the mother and infant. In particular, randomised control trials to investigate whether serial antenatal clinic and ultrasound assessments of suspected LGA infants (including liquor volume and markers of fetal adiposity) would be useful, to assess whether surveillance methods improve health outcomes. In addition, as there are concerns that identifying suspected LGA fetuses may lead to unnecessary maternal anxiety, investigations and interventions, any such trial would need to assess the risks as well as benefits of regimens of fetal surveillance for suspected LGA fetuses.

Disparities in Access to Prenatal Care Services for African Immigrant Women in Spain

This retrospective cohort study compares the utilization of prenatal care between African immigrant and native Spanish women. For 2007-2010, we identified 231 pregnant African immigrant women. The native-born population sample was obtained by simple random sampling in a 1:3 ratio. The Kessner Index (KI) and our Own Index (OI) were applied to rate prenatal care adequacy in three categories (adequate, intermediate, and inadequate). Odds ratios (ORs) were estimated using non-conditional logistic regression. Prenatal care was adequate according to the indexes (KI or OI) in 21.3 and 25.8% of North Africans and in 22.5 and 30.4% of sub-Saharan Africans. The ORs of inadequacy when adjusted for maternal age, social risk factors, and previous reproductive outcomes were 30.32 and 35.47 (KI or OI) in North and 64.43 and 67.93 in sub- Saharan Africans. These results suggest significant differences in obtaining adequate prenatal care between immigrant and native Spanish women.

Modifiable risk factors for term large for gestational age births

To determine modifiable and nonmodifiable risk factors for term large for gestational age (T-LGA) births in Northern and Central Alberta and their public health importance, a retrospective cohort study (n = 115,198) of singleton live births (1996-2003) was conducted using maternal and newborn data from a provincial perinatal database. After adjusting for potential confounders, predictors of T-LGA births included prepregnancy weight 91 kg or greater, multiparity, and previous LGA birth. The strongest modifiable predictor was prepregnancy weight 91 kg or greater (OR = 2.52; CI 2.39, 2.65). The population-attributable risk percentage for prepregnancy weight 91 kg or greater was 10%.