Machine learning is used to study growth of a metal-organic framework (MOF) in a high-dimensional synthetic space. Neural networks for image processing also provide tools for automatically measuring thickness and lateral size of MOF nanoplates to provide quantitative data for further analysis. Relationships among different quantities in these synthetic endeavors were searched and evaluated with state-of-the-art mathematical tools. This works highlights new opportunities in using machine learning to expedite materials development and provides insight into their synthesis process.

ObjectiveThe aim of this study is to develop multistage prediction models for pre-eclampsia (PE) covering almost the entire pregnancy period based on routine antenatal measurements and to propose a risk screening strategy.MethodsThis was a retrospective cohort study that included 20582 singleton pregnant women with the last menstruation between January 1, 2013 and December 31, 2019. Of the 20582 women, 717 (3.48%) developed pre-eclampsia, including 46 (0.22%) with early-onset pre-eclampsia and 119 (0.58%) preterm pre-eclampsia. We randomly divided the dataset into the training set (N = 15665), the testing set (N = 3917), and the validation set (N = 1000). Least Absolute Shrinkage And Selection Operator (LASSO) was used to do variable selection from demographic characteristics, blood pressure, blood routine examination and biochemical tests. Logistic regression was used to develop prediction models at eight periods: 5–10 weeks, 11–13 weeks, 14–18 weeks, 19–23 weeks, 24–27 weeks, 28–31 weeks, 32–35 weeks, and 36–39 weeks of gestation. We calculated the AUROC (Area Under the Receiver Operating Characteristic Curve) on the test set and validated the screening strategy on the validation set.ResultsWe found that uric acid tested from 5–10 weeks of gestation, platelets tested at 18–23 and 24–31 weeks of gestation, and alkaline phosphatase tested at 28–31, 32–35 and 36–39 weeks of gestation can further improve the prediction performance of models. The AUROC of the optimal prediction models on the test set gradually increased from 0.71 at 5–10 weeks to 0.80 at 24–27 weeks, and then gradually increased to 0.95 at 36–39 weeks of gestation. At sensitivity level of 0.98, our screening strategy can identify about 94.8% of women who will develop pre-eclampsia and reduce about 40% of the healthy women to be screened by 28–31 weeks of pregnancy.ConclusionWe developed multistage prediction models and a risk screening strategy, biomarkers of which were part of routine test items and did not need extra costs. The prediction window has been advanced to 5–10 weeks, which has allowed time for aspirin intervention and other means for PE high-risk groups.

Background: Preterm birth (PTB) leads to short-term and long-term adverse effects on newborns. Exposure to fine particulate matter (PM2.5) was positively related to PTB. However, the global annual average PM2.5 was three times than the recommended value in 1998–2014. Socio-demographic index (SDI) is a new indicator that comprehensively reflects the overall development level of a country, partly because of “the epidemiological transition”. Among other countries with higher and similar SDI levels, policy makers have the opportunity to learn from their successful experiences and avoid their mistakes by identifying whether their burdens of disease are higher or lower than the expected. However, it is unclear about the trends of the burden of PM2.5-related preterm birth in different countries and different levels of SDI regions. Additionally, the relationship between the SDI and the burden in 1990–2019 is also unclear. Methods: This was a retrospective study based on the Global Burden of Disease Study 2019 (GBD2019) database from 1990 to 2019. The burden of PM2.5-related PTB was measured by the age-standardized mortality rate (ASMR), age-standardized disability-adjusted life years rate (ASDR), mortality rate, and the disability-adjusted life years (DALYs). The annual percentage changes (APCs) and the average annual percentage changes (AAPCs) were used to reflect the trends over the past 30 years, which were calculated using a joinpoint model. The relationships between the ASMR, ASDR, and SDI were calculated using a Gaussian process regression. Findings: In 2019, the entire burden of PM2.5-related PTB was relatively high, where the ASMR and the ASDR were 0.76 and 67.71, increasing by 7.04% and 7.12%, respectively. It mainly concentrated on early neonates, boys, and on low-middle SDI regions. The increase in the burden of PM2.5-related PTB in low and low-middle SDI regions is slightly higher than the decrease in other SDI regions. In 2019, the burden varied greatly among different levels of SDI regions where ASMRs varied from 0.13 in high SDI regions to 1.19 in low-middle regions. The relationship between the expected value of the burden of PM2.5-related PTB and SDI presented an inverted U-shape, and it reached the maximum when SDI is around 0.50. The burdens in four regions (South Asia, North Africa and the Middle East, western sub-Saharan Africa, and southern sub-Saharan Africa) were much higher than the mean value. Boys bore more burden that girls. The sex ratio (boys:girls) of the burden showed a dramatically increasing trend in low SDI regions and a decreasing trend in middle SDI regions and high-middle SDI regions. These differences reflect the huge inequality among regions, countries, ages, and sex in the burden of PM2.5-related PTB. Conclusion: The overall burden of PM2.5-related PTB in 2019 was relatively high, mainly concentrated on early neonates, boys, and on low-middle SDI regions. It showed an increasing trend in low-middle and low SDI regions. The association between the burden and the SDI presented an inverted U-shape. It is very necessary to promulgate policies to prevent and control air pollution in countries with large and increasing exposure to PM2.5 pollution because it does not need action at an individual level. Focusing on public educational interventions, public and professional policies, and improving accessibility of prenatal care are other feasible ways for low and low-middle SDI countries. Policy makers should also appropriately allocate medical resources to boys and early newborns.

No abstract