Periconceptional Folic Acid Only Versus Multiple Micronutrients Containing Folic Acid and Association with Gestational Diabetes Mellitus - Beijing Municipality, China, 2017-2021.

What is already known about this topic?: Inconsistent results have been reported on the association between periconceptional folic acid only (FAO) or multiple micronutrients containing folic acid (MMFA) supplementation and the risk of gestational diabetes mellitus (GDM) in previous research. What is added by this report?: In a prospective cohort study conducted among pregnant women in Haidian District, Beijing Municipality, it was observed that those who took MMFA demonstrated a higher likelihood of developing GDM in comparison to those who consumed FAO periconceptionally. Interestingly, the increased risk for GDM in pregnant women supplemented with MMFA compared to FAO was primarily due to changes in fasting plasma glucose. What are the implications for public health practice?: It is highly recommended that women prioritize the use of FAO in order to yield potential benefits in the prevention of GDM.

Motor intent recognition of multi-feature fusion EEG signals by UMAP algorithm.

The key to the analysis of electroencephalogram (EEG) signals lies in the extraction of effective features from the raw EEG signals, which can then be utilized to augment the classification accuracy of motor imagery (MI) applications in brain-computer interface (BCI). It can be argued that the utilization of features from multiple domains can be a more effective approach to feature extraction for MI pattern classification, as it can provide a more comprehensive set of information that the traditional single feature extraction method may not be able to capture. In this paper, a multi-feature fusion algorithm based on uniform manifold approximate and projection (UMAP) is proposed for motor imagery EEG signals. The brain functional network and common spatial pattern (CSP) are initially extracted as features. Subsequently, UMAP is utilized to fuse the extracted multi-domain features to generate low-dimensional features with improved discriminative capability. Finally, the k-nearest neighbor (KNN) classifier is applied in a lower dimensional space. The proposed method is evaluated using left-right hand EEG signals, and achieved the average accuracy of over 92%. The results indicate that, compared with single-domain-based feature extraction methods, multi-feature fusion EEG signal classification based on the UMAP algorithm yields superior classification and visualization performance. Feature extraction and fusion based on UMAP algorithm of left-right hand motor imagery.