Prevalence of term low birth weight andits determinants in Shanghai, China

Objective: To investigate the prevalence of term low birth weight (TLBW) and its risk factors. Methods: A follow-up study with 7, 872 couples was conducted from 1987 to 199o beginning from the time they got marriage licenses in two districts defined in Shanghai. They were interviewed in the third month and again in the fifteenth month and in the fifth to sixth year afterwards individually at home. The total follow up rate reached 98%. Couple’s background characteristics as well as the information on their general health. reproductivc history and contraceptive use etc.. were collected dynamically. All of the single live births with term delivery were Included for data analysis in this paper. Adjusted odd ratios and population attributable risk (PAR%) were computed. Results: The prevalence of TLBW in Shanghai single term live births was 2. 0% (134,/6.573), represents 54. 7% (134/245) of the total low birth weights in our sam pie. Significant social and behaviour risk factors relating with TI-BW were wife’s dissat- isfaction with marriage; low education level of husband; co-residence with parents during pregnancy; heavy housework done by the wife while being pregnant. Significant biomedical risky factors were menarche age greater than 16 years old; maternal age at delivery greater than 29 years old; maternal body mass index less than 19. 8; wife suf- fered from serious disease prior to conceiving; having pregnancy complication; gestational weight gain less than 20 % of pre-pregnancy weight; having abortion, stillbirth and fetal death history. Conclusion: TL.BW constituted over half of all low birth weights in Shanghai. Special attention should be paid to the determinants mentioned above in TLBW intervention program. Improving couples’ economic and living condition and husband ’s education at tainment, and caloric supplementation with women while being pregnant would all be particularly effective in reducing the occurrence of TLBW in Shnaghai.

Supervised Contrastive Learning with Term Weighting for Improving Chinese Text Classification

With the rapid growth of information retrieval technology,Chinese text classification,which is the basis of information content security,has become a widely discussed topic.In view of the huge difference compared with English,Chinese text task is more complex in semantic information representations.However,most existing Chinese text classification approaches typically regard feature representation and feature selection as the key points,but fail to take into account the learning strategy that adapts to the task.Besides,these approaches compress the Chinese word into a representation vector,without considering the distribution of the term among the categories of interest.In order to improve the effect of Chinese text classification,a unified method,called Supervised Contrastive Learning with Term Weighting(SCL-TW),is proposed in this paper.Supervised contrastive learning makes full use of a large amount of unlabeled data to improve model stability.In SCL-TW,we calculate the score of term weighting to optimize the process of data augmentation of Chinese text.Subsequently,the transformed features are fed into a temporal convolution network to conduct feature representation.Experimental verifications are conducted on two Chinese benchmark datasets.The results demonstrate that SCL-TW outperforms other advanced Chinese text classification approaches by an amazing margin.