Association between preterm births and socioeconomic development: analysis of national data

Montemor, Marina Sanches; Demarque, Gabriella Ferreira; Rodrigues, Agatha Sacramento; Francisco, Rossana Pulcinelli Vieira; Carvalho, Mário Henrique Burlacchini de

doi:10.1186/s12889-022-14376-2

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The association between payment method and preterm birth is a complex issue. Research has revealed that socioeconomic status can be a contributing factor to preterm birth, with women who lack insurance or have public insurance being more susceptible to preterm birth compared to those with private insurance ( 37 ). One possible explanation for this correlation is that women with lower incomes may encounter more obstacles in accessing healthcare services, including prenatal care, which can elevate the risk of preterm birth.…”

Section: Discussionmentioning

confidence: 99%

Predicting preterm birth using auto-ML frameworks: a large observational study using electronic inpatient discharge data

Kong,

Tao,

Xiao

et al. 2024

Front. Pediatr.

View full text Add to dashboard Cite

BackgroundTo develop and compare different AutoML frameworks and machine learning models to predict premature birth.MethodsThe study used a large electronic medical record database to include 715,962 participants who had the principal diagnosis code of childbirth. Three Automatic Machine Learning (AutoML) were used to construct machine learning models including tree-based models, ensembled models, and deep neural networks on the training sample (N = 536,971). The area under the curve (AUC) and training times were used to assess the performance of the prediction models, and feature importance was computed via permutation-shuffling.ResultsThe H2O AutoML framework had the highest median AUC of 0.846, followed by AutoGluon (median AUC: 0.840) and Auto-sklearn (median AUC: 0.820), and the median training time was the lowest for H2O AutoML (0.14 min), followed by AutoGluon (0.16 min) and Auto-sklearn (4.33 min). Among different types of machine learning models, the Gradient Boosting Machines (GBM) or Extreme Gradient Boosting (XGBoost), stacked ensemble, and random forrest models had better predictive performance, with median AUC scores being 0.846, 0.846, and 0.842, respectively. Important features related to preterm birth included premature rupture of membrane (PROM), incompetent cervix, occupation, and preeclampsia.ConclusionsOur study highlights the potential of machine learning models in predicting the risk of preterm birth using readily available electronic medical record data, which have significant implications for improving prenatal care and outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting preterm birth using auto-ML frameworks: a large observational study using electronic inpatient discharge data

Kong,

Tao,

Xiao

et al. 2024

Front. Pediatr.

View full text Add to dashboard Cite

show abstract

Fine Particulate Matter, Its Constituents, and Spontaneous Preterm Birth

Jiao,

Reilly,

Benmarhnia

et al. 2024

JAMA Netw Open

View full text Add to dashboard Cite

ImportanceThe associations of exposure to fine particulate matter (PM2.5) and its constituents with spontaneous preterm birth (sPTB) remain understudied. Identifying subpopulations at increased risk characterized by socioeconomic status and other environmental factors is critical for targeted interventions.ObjectiveTo examine associations of PM2.5 and its constituents with sPTB.Design, Setting, and ParticipantsThis population-based retrospective cohort study was conducted from 2008 to 2018 within a large integrated health care system, Kaiser Permanente Southern California. Singleton live births with recorded residential information of pregnant individuals during pregnancy were included. Data were analyzed from December 2023 to March 2024.ExposuresDaily total PM2.5 concentrations and monthly data on 5 PM2.5 constituents (sulfate, nitrate, ammonium, organic matter, and black carbon) in California were assessed, and mean exposures to these pollutants during pregnancy and by trimester were calculated. Exposures to total green space, trees, low-lying vegetation, and grass were estimated using street view images. Wildfire-related exposure was measured by the mean concentration of wildfire-specific PM2.5 during pregnancy. Additionally, the mean exposure to daily maximum temperature during pregnancy was calculated.Main Outcomes and MeasuresThe primary outcome was sPTB identified through a natural language processing algorithm. Discrete-time survival models were used to estimate associations of total PM2.5 concentration and its 5 constituents with sPTB. Interaction terms were used to examine the effect modification by race and ethnicity, educational attainment, household income, and exposures to green space, wildfire smoke, and temperature.ResultsAmong 409 037 births (mean [SD] age of mothers at delivery, 30.3 [5.8] years), there were positive associations of PM2.5, black carbon, nitrate, and sulfate with sPTB. Adjusted odds ratios (aORs) per IQR increase were 1.15 (95% CI, 1.12-1.18; P &lt; .001) for PM2.5 (IQR, 2.76 μg/m3), 1.15 (95% CI, 1.11-1.20; P &lt; .001) for black carbon (IQR, 1.05 μg/m3), 1.09 (95% CI, 1.06-1.13; P &lt; .001) for nitrate (IQR, 0.93 μg/m3), and 1.06 (95% CI, 1.03-1.09; P &lt; .001) for sulfate (IQR, 0.40 μg/m3) over the entire pregnancy. The second trimester was the most susceptible window; for example, aORs for total PM2.5 concentration were 1.07 (95% CI, 1.05-1.09; P &lt; .001) in the first, 1.10 (95% CI, 1.08-1.12; P &lt; .001) in the second, and 1.09 (95% CI, 1.07-1.11; P &lt; .001) in the third trimester. Significantly higher aORs were observed among individuals with lower educational attainment (eg, less than college: aOR, 1.16; 95% CI, 1.12-1.21 vs college [≥4 years]: aOR, 1.10; 95% CI, 1.06-1.14; P = .03) or income (&lt;50th percentile: aOR, 1.17; 95% CI, 1.14-1.21 vs ≥50th percentile: aOR, 1.12; 95% CI, 1.09-1.16; P = .02) or who were exposed to limited green space (&lt;50th percentile: aOR, 1.19; 95% CI, 1.15-1.23 vs ≥50th percentile: aOR, 1.12; 95% CI, 1.09-1.15; P = .003), more wildfire smoke (≥50th percentile: aOR, 1.19; 95% CI, 1.16-1.23 vs &lt;50th percentile: aOR, 1.13; 95% CI, 1.09-1.16; P = .009), or extreme heat (aOR, 1.51; 95% CI, 1.42-1.59 vs mild temperature: aOR, 1.11; 95% CI, 1.09-1.14; P &lt; .001).Conclusions and RelevanceIn this study, exposures to PM2.5 and specific PM2.5 constituents during pregnancy were associated with increased odds of sPTB. Socioeconomic status and other environmental exposures modified this association.

show abstract

Association between preterm births and socioeconomic development: analysis of national data

Cited by 2 publications

References 34 publications

Predicting preterm birth using auto-ML frameworks: a large observational study using electronic inpatient discharge data

Predicting preterm birth using auto-ML frameworks: a large observational study using electronic inpatient discharge data

Fine Particulate Matter, Its Constituents, and Spontaneous Preterm Birth

Contact Info

Product

Resources

About