Machine learning guided postnatal gestational age assessment using new-born screening metabolomic data in South Asia and sub-Saharan Africa

BACKGROUND

Babies born early and/or small for gestational age in Low and Middle-income countries (LMICs) contribute substantially to global neonatal and infant mortality. Tracking this metric is critical at a population level for informed policy, advocacy, resources allocation and program evaluation and at an individual level for targeted care. Early prenatal ultrasound examination is not available in these settings, gestational age (GA) is estimated using new-born assessment, last menstrual period (LMP) recalls and birth weight, which are unreliable. Algorithms in developed settings, using metabolic screen data, provided GA estimates within 1-2 weeks of ultrasonography-based GA. We sought to leverage machine learning algorithms to improve accuracy and applicability of this approach to LMICs settings.

METHODS

This study uses data from AMANHI-ACT, a prospective pregnancy cohorts in Asia and Africa where early pregnancy ultrasonography estimated GA and birth weight are available and metabolite screening data in a subset of 1318 new-borns were also available. We utilized this opportunity to develop machine learning (ML) algorithms. Random Forest Regressor was used where data was randomly split into model-building and model-testing dataset. Mean absolute error (MAE) and root mean square error (RMSE) were used to evaluate performance. Bootstrap procedures were used to estimate confidence intervals (CI) for RMSE and MAE. For pre-term birth identification ROC analysis with bootstrap and exact estimation of CI for area under curve (AUC) were performed.

RESULTS

Overall model estimated GA had MAE of 5.2 days (95% CI 4.6-6.8), which was similar to performance in SGA, MAE 5.3 days (95% CI 4.6-6.2). GA was correctly estimated to within 1 week for 85.21% (95% CI 72.31-94.65). For preterm birth classification, AUC in ROC analysis was 98.1% (95% CI 96.0-99.0; p < 0.001). This model performed better than Iowa regression, AUC Difference 14.4% (95% CI 5-23.7; p = 0.002).

CONCLUSIONS

Machine learning algorithms and models applied to metabolomic gestational age dating offer a ladder of opportunity for providing accurate population-level gestational age estimates in LMICs settings. These findings also point to an opportunity for investigation of region-specific models, more focused feasible analyte models, and broad untargeted metabolome investigation.

Short-term effects of Saharan dust intrusions and biomass combustion on birth outcomes in Spain

The objective of this study is to analyze the short-term effects of atmospheric pollutant concentrations (PM₁₀, NO₂ and O₃) and heat and cold waves on the number of pre-term births and cases of low birth weight related to Saharan dust advection and biomass combustion. The dependent variables used in this analysis were the total number of births, births with low weight (>2.500 g) and pre-term births (<37 weeks), that occurred at the province level. Data provided by the NSI included: days with Saharan dust intrusion or biomass advection classified in terms of information provided by MITECO for each of the nine regions in Spain. A representative city was selected for reach region in which the registered average daily concentrations of PM₁₀, NO₂ and O₃ (μg/m³) were used. These were also provided by MITECO. The daily maximum and daily minimum temperature (°C) used was those registered by the meteorological observatory station located in each province capital, provided by AEMET. Using Poisson log linear regression models, the associated relative risks (RR) were measured as well as the population attributable risk (PAR) corresponding to the variables that resulted statistically significant at p < 0.05 for days with and without intrusion of natural particulate matter. The results obtained show that the days with Saharan dust intrusion or advections due to biomass combustion- beyond the impact of PM₁₀, primary pollutants such as NO₂ (in Saharan intrusions), heat waves and O₃ - are associated with the number of births, low birth weight and pre-term birth. The RR and percent PAR of the pollutants and the heat waves are greater than those obtained for PM₁₀. The results of this study indicate that days with natural particulate matter due to biomass combustion or advection of Saharan dust put pregnant women at risk.