BACKGROUND: There are abundant studies on COVID-19 but few on its impact on hepatitis E. We aimed to assess the effect of the COVID-19 countermeasures on the pattern of hepatitis E incidence and explore the application of time series models in analyzing this pattern.
METHODS: Our pivotal idea was to fit a pre-COVID-19 model with data from before the COVID-19 outbreak and use the deviation between forecast values and actual values to reflect the effect of COVID-19 countermeasures. We analyzed the pattern of hepatitis E incidence in China from 2013 to 2018. We evaluated the fitting and forecasting capability of 3 methods before the COVID-19 outbreak. Furthermore, we employed these methods to construct pre-COVID-19 incidence models and compare post-COVID-19 forecasts with reality.
RESULTS: Before the COVID-19 outbreak, the Chinese hepatitis E incidence pattern was overall stationary and seasonal, with a peak in March, a trough in October, and higher levels in winter and spring than in summer and autumn, annually. Nevertheless, post-COVID-19 forecasts from pre-COVID-19 models were extremely different from reality in sectional periods but congruous in others.
CONCLUSIONS: Since the COVID-19 pandemic, the Chinese hepatitis E incidence pattern has altered substantially, and the incidence has greatly decreased. The effect of the COVID-19 countermeasures on the pattern of hepatitis E incidence was temporary. The incidence of hepatitis E was anticipated to gradually revert to its pre-COVID-19 pattern.

BACKGROUND: Improving the accuracy of estimated fetal weight (EFW) calculation can contribute to decision-making for obstetricians and decrease perinatal complications. This study aimed to develop a deep neural network (DNN) model for EFW based on obstetric electronic health records.
METHODS: This study retrospectively analyzed the electronic health records of pregnant women with live births delivery at the obstetrics department of International Peace Maternity & Child Health Hospital between January 2016 and December 2018. The DNN model was evaluated using Hadlock\'s formula and multiple linear regression.
RESULTS: A total of 34824 live births (23922 primiparas) from 49896 pregnant women were analyzed. The root-mean-square error of DNN model was 189.64 g (95% CI 187.95 g-191.16 g), and the mean absolute percentage error was 5.79% (95%CI: 5.70%-5.81%), significantly lower compared to Hadlock\'s formula (240.36 g and 6.46%, respectively). By combining with previously unreported factors, such as birth weight of prior pregnancies, a concise and effective DNN model was built based on only 10 parameters. Accuracy rate of a new model increased from 76.08% to 83.87%, with root-mean-square error of only 243.80 g.
CONCLUSIONS: Proposed DNN model for EFW calculation is more accurate than previous approaches in this area and be adopted for better decision making related to fetal monitoring.