An early screening model for preeclampsia: utilizing zero-cost maternal predictors exclusively.

To provide a reliable, low-cost screening model for preeclampsia, this study developed an early screening model in a retrospective cohort (25,709 pregnancies) and validated in a validation cohort (1760 pregnancies). A data augmentation method (α-inverse weighted-GMM + RUS) was applied to a retrospective cohort before 10 machine learning models were simultaneously trained on augmented data, and the optimal model was chosen via sensitivity (at a false positive rate of 10%). The AdaBoost model, utilizing 16 predictors, was chosen as the final model, achieving a performance beyond acceptable with Area Under the Receiver Operating Characteristic Curve of 0.8008 and sensitivity of 0.5190. All predictors were derived from clinical characteristics, some of which were previously unreported (such as nausea and vomiting in pregnancy and menstrual cycle irregularity). Compared to previous studies, our model demonstrated superior performance, exhibiting at least a 50% improvement in sensitivity over checklist-based approaches, and a minimum of 28% increase over multivariable models that solely utilized maternal predictors. We validated an effective approach for preeclampsia early screening incorporating zero-cost predictors, which demonstrates superior performance in comparison to similar studies. We believe the application of the approach in combination with high performance approaches could substantially increase screening participation rate among pregnancies. Machine learning model for early preeclampsia screening, using 16 zero-cost predictors derived from clinical characteristics, was built on a 10-year Chinese cohort. The model outperforms similar research by at least 28%; validated on an independent cohort.

A Preliminary Investigation of Naturally Occurring Aluminum in Grains, Vegetables, and Fruits from Some Areas of China and Dietary Intake Assessment.

An investigation of the naturally occurring aluminum contents in grains, fruits and vegetables locally planted in some areas of China was conducted, and the aluminum dietary intake from the investigated food was estimated. A total of 2,469 samples were collected during 2013 to 2014 and tested for aluminum content using ICP-MS method. The results showed that although 77.6% of the samples contained aluminum less than 5 mg/kg, significant variations of aluminum contents were observed in different food groups. Generally, the aluminum contents were found to be relatively high in dried grains and fresh vegetables, and low in fresh fruits. The mean value of aluminum contents in grains was 6.3 mg/kg, with wheat being the highest, followed by soybean and corn. The fresh vegetables had an average aluminum content of 4.7 mg/kg, with leafy vegetables being the highest, followed by bulb and stem vegetables. Most varieties of fresh fruits were low in aluminum, with the mean of 1.3 mg/kg. Based on the food consumption data from the China National Nutrient and Health Survey, the average weekly dietary intake of naturally occurring aluminum from the investigated foods was estimated to be 0.62 mg/kg bw for the general population and 0.55 to 1.00 mg/kg bw for different age groups. Grains and vegetables were the main contributors to the overall intake. Evaluated against the provisional tolerable weekly intake (PTWI) of 2 mg/kg bw, the dietary naturally occurring aluminum intake from the investigated foods was considered to be no safety concern.