Objective:To explore the application and effect of artificial intelligence technology in perinatal management of gestational diabetes mellitus.Methods:240 pregnant women with gestational diabetes diagnosed during 24-26 weeks of pregnancy in Changsha Maternal and Child Health Hospital were prospectively selected and randomly divided into control group (120 cases) and observation group (120 cases). The control group used the traditional management mode for nutritional management, and the observation group used AI technology for nutritional management. The weight gain, blood glucose control level, insulin use, pregnancy complications, pregnancy outcome and other indicators of the two groups were compared.Results:(1) Monitoring indicators during pregnancy: there was no significant difference in weight gain between the two groups ( P>0.05). The proportion of weight gain in the appropriate range in the observation group was significantly higher than that in the control group ( P<0.05); The prevalence of full-term anemia, insulin use rate and the incidence of blood glucose exceeding the control standard in the observation group were significantly higher than those in the control group (all P<0.05). (2) Pregnancy outcome: there was no significant difference in the incidence of gestational hypertension, cesarean section, fetal growth restriction, premature delivery and neonatal hypoglycemia between the two groups (all P>0.05); The incidence of conversion to cesarean section, macrosomia, neonatal blood glucose <2.6 mmol/L, mild asphyxia and admission to neurosurgical intensive care unit (NICU) in the observation group were significantly higher than those in the control group (all P<0.05). Conclusions:Application of AI technology to nutritional management of gestational diabetes can better control the maternal perinatal weight gain and blood glucose level, reduce the incidence of anemia in the third trimester of pregnancy, the incidence of macrosomia, the use of insulin and the rate of conversion to cesarean section, and improve the neonatal outcome.

Objective To explore the effect of timosaponin B-II ( TB-II) on the differentiation of neural stem cells (NSCs) into tyrosine hydroxylase (TH) positive neurons in neonatal rats. Methods The biological functions of self-proliferation and multi-differentiation of NSCs were identified by primary culture, cell proliferation counting,morphological observation and immunology. NSCs of SD rats were cultured in vitro and treated with different concentrations of TB-II (10 μg/ml,30 μg/ml ,100 μg/ml) for 7 days. Immuno-histochemistry was used to detect the effect of TB-II on the differentiation of NSCs into TH-positive neurons, and Western blot was used to detect the expression of TH protein in neurons. Results ( 1) The cultured cells had the ability to self-proliferation,expressed nestin protein and differentiated into neurons and glial cells. So the cultured cells were conformed to the biological function of neural stem cells. (2)Compared with the control group,the TH positive cell ratio of TB-II 30 μg/ml group and TB-II 100 μg/ml group increased ((10. 03± 1. 36)%),( 20. 01± 3. 37)%),(31. 32± 3. 98)%) ,the difference was significant ( t=6. 15, 16. 54,both P<0. 05). There was no significant difference between TB-II 10 μg/ml group and control group (P>0. 05). (3)Western results showed that the relative expression of TH protein in TB-II 30 g/ml group and TB-II 100 μg/ml group was higher than that in control group,the difference was statistically significant (con-trol group: (1. 02±0. 24),TB-II 30μg/ml group: (3. 64±1. 78),TB-II 100 μg/ml group: (5. 88±2. 34);t=12. 58,9. 15,both P<0. 05). There was no significant difference between TB-II 10 μg/ml group and con-trol group (P>0. 05). Conclusion TB-II can promote the differentiation of NSCs into TH-positive neurons.