Search

Pathfinder Normalized Difference Vegetation Index (NDVI) derived from Channel 1 (Red) and Channel 2 (near-infrared) of Advanced Very High Resolution Radiometer (AVHRR) onboard NOAA 14 became abnormally high for the 10-day composite from February 11 to 20 in 1999 for Western Australia. There was a solar eclipse in the satellite path on February 16 about the same time when NOAA 14 was above the eclipse location, causing the Channel 1 value to be 0 in many cells. The NDVI composite updating rule was to capture the greenest condition of each composite period. There seems to have been a possible lack of quality control during the NDVI composite generation, which could have caused the abnormally high NDVI values. However, there were some cells within the affected area that had values close to normal for NDVI as well as Channel 1 and Channel 2. The abnormal NDVI data values could have been avoided by not using the data obtained during the eclipse in the generation of the composite. Further investigation on those cells which were not affected by the eclipse is suggested for a better quality control of remote sensing data obtained during eclipse occurrences. [ABSTRACT FROM AUTHOR]

Background: There is limited and inconsistent evidence on the risk of ambient temperature on small for gestational age (SGA) and there are no known related studies for large for gestational age (LGA). In addition, previous studies used temperature rather than a biothermal metric., Objectives: Our aim was to examine the associations and critical susceptible windows of maternal exposure to a biothermal metric [Universal Thermal Climate Index (UTCI)] and the hazards of SGA and LGA., Methods: We linked 385,337 singleton term births between 1 January 2000 and 31 December 2015 in Western Australia to daily spatiotemporal UTCI. Distributed lag nonlinear models with Cox regression and multiple models were used to investigate maternal exposure to UTCI from 12 weeks preconception to birth and the adjusted hazard ratios (HRs) of SGA and LGA., Results: Relative to the median exposure, weekly and monthly specific exposures showed potential critical windows of susceptibility for SGA and LGA at extreme exposures, especially during late gestational periods. Monthly exposure showed strong positive associations from the 6th to the 10th gestational months with the highest hazard of 13% for SGA ( HR = 1.13 ; 95% CI: 1.10, 1.14) and 7% for LGA ( HR = 1.07 ; 95% CI: 1.03, 1.11) at the 10th month for the 1st UTCI centile. Entire pregnancy exposures showed the strongest hazards of 11% for SGA ( HR = 1.11 ; 95% CI: 1.04, 1.18) and 3% for LGA ( HR = 1.03 ; 95% CI: 0.95, 1.11) at the 99th UTCI centile. By trimesters, the highest hazards were found during the second and first trimesters for SGA and LGA, respectively, at the 99th UTCI centile. Based on estimated interaction effects, male births, mothers who were non-Caucasian, smokers, ≥ 35 years of age, and rural residents were most vulnerable., Conclusions: Both weekly and monthly specific extreme biothermal stress exposures showed potential critical susceptible windows of SGA and LGA during late gestational periods with disproportionate sociodemographic vulnerabilities. https://doi.org/10.1289/EHP12660.

Preterm birth is a global public health problem with a significant burden on the individuals affected. The study aimed to extend current research on preterm birth prognostic model development by developing and internally validating models using machine learning classification algorithms and population-based routinely collected data in Western Australia. The longitudinal retrospective cohort study involved all births in Western Australia between 1980 and 2015, and the analytic sample contains 81,974 (8.6%) preterm births (< 37 weeks of gestation). Prediction models for preterm birth were developed using regularised logistic regression, decision trees, Random Forests, extreme gradient boosting, and multi-layer perceptron (MLP). Predictors included maternal socio-demographics and medical conditions, current and past pregnancy complications, and family history. Class weight was applied to handle imbalanced outcomes and stratified tenfold cross-validation was used to reduce overfitting. Close to half of the preterm births (49.1% at 5% FPR, 95% CI 48.9%,49.5%) were correctly classified by the best performing classifier (MLP) for all women when current pregnancy information was available. The sensitivity was boosted to 52.7% (95% CI 52.1%,53.3%) after including past obstetric history in a sub-population of births from multiparous women. Around half of the preterm birth can be identified antenatally at high specificity using population-based routinely collected maternal and pregnancy data. The performance of the prediction models depends on the available predictor pool that is individual and time specific., (© 2022. The Author(s).)

Quantification of stillbirth risk has potential to support clinical decision-making. Studies that have attempted to quantify stillbirth risk have been hampered by small event rates, a limited range of predictors that typically exclude obstetric history, lack of validation, and restriction to a single classifier (logistic regression). Consequently, predictive performance remains low, and risk quantification has not been adopted into antenatal practice. The study population consisted of all births to women in Western Australia from 1980 to 2015, excluding terminations. After all exclusions there were 947,025 livebirths and 5,788 stillbirths. Predictive models for stillbirth were developed using multiple machine learning classifiers: regularised logistic regression, decision trees based on classification and regression trees, random forest, extreme gradient boosting (XGBoost), and a multilayer perceptron neural network. We applied 10-fold cross-validation using independent data not used to develop the models. Predictors included maternal socio-demographic characteristics, chronic medical conditions, obstetric complications and family history in both the current and previous pregnancy. In this cohort, 66% of stillbirths were observed for multiparous women. The best performing classifier (XGBoost) predicted 45% (95% CI: 43%, 46%) of stillbirths for all women and 45% (95% CI: 43%, 47%) of stillbirths after the inclusion of previous pregnancy history. Almost half of stillbirths could be potentially identified antenatally based on a combination of current pregnancy complications, congenital anomalies, maternal characteristics, and medical history. Greatest sensitivity is achieved with addition of current pregnancy complications. Ensemble classifiers offered marginal improvement for prediction compared to logistic regression.