[UGT1A1 gene mutations in Chinese Dong neonates in Sanjiang, Guangxi]. / 广西三江县侗族新生儿UGT1A1åŸºå› å˜å¼‚åˆ†æž.

OBJECTIVES: To study the characteristics of UGT1A1 gene mutations in Dong neonates in Sanjiang County of Liuzhou and its association with the pathogenesis of hyperbilirubinemia in Dong neonates. METHODS: A prospective analysis was performed on 84 neonates who were diagnosed with unexplained hyperbilirubinemia in the Department of Neonatology, Sanjiang County People's Hospital, from January 2021 to January 2022. Sixty healthy neonates born during the same period were enrolled as the control group. Peripheral blood genomic DNA was extracted for both groups, and UGT1A1 exon 1 was amplified by PCR and sequenced. RESULTS: In the case group, 33 neonates were found to have G71R missense mutation, with a mutation rate of 39%. The case group had a significantly higher frequency of A allele than the healthy control group (21% vs 10%, P<0.05). The risk of hyperbilirubinemia in Dong neonates carrying G71R missense mutation was 2.588 times as high as that in healthy neonates carrying wild-type UGT1A1 gene (P<0.05). Hardy-Weinberg equilibrium testing showed that the UGT1A1 G71R locus was in genetic equilibrium in both groups (P>0.05). CONCLUSIONS: UGT1A1 G71R mutation is a high-frequency gene mutation type in Dong neonates in Sanjiang County, and G71R missense mutation is associated with hyperbilirubinemia in Dong neonates.

[Epilepsy detection and analysis method for specific patient based on data augmentation and deep learning].

In recent years, epileptic seizure detection based on electroencephalogram (EEG) has attracted the widespread attention of the academic. However, it is difficult to collect data from epileptic seizure, and it is easy to cause over fitting phenomenon under the condition of few training data. In order to solve this problem, this paper took the CHB-MIT epilepsy EEG dataset from Boston Children's Hospital as the research object, and applied wavelet transform for data augmentation by setting different wavelet transform scale factors. In addition, by combining deep learning, ensemble learning, transfer learning and other methods, an epilepsy detection method with high accuracy for specific epilepsy patients was proposed under the condition of insufficient learning samples. In test, the wavelet transform scale factors 2, 4 and 8 were set for experimental comparison and verification. When the wavelet scale factor was 8, the average accuracy, average sensitivity and average specificity was 95.47%, 93.89% and 96.48%, respectively. Through comparative experiments with recent relevant literatures, the advantages of the proposed method were verified. Our results might provide reference for the clinical application of epilepsy detection.