Trends and prediction in the incidence rate of hepatitis C in Shandong Province in China from 2004 to 2030.

BACKGROUND: Hepatitis C threatens human health and brings a heavy economic burden. Shandong Province is the second most populous province in China and has uneven regional economic development. Therefore, we analyzed the incidence rate trend and regional differences of hepatitis C in Shandong Province from 2004 to 2021. METHODS: The monthly and annual incidence rates of hepatitis C in Shandong Province from 2022 to 2030 were predicted by fitting Autoregressive Integrated Moving Average model (ARIMA), Long Short-Term Memory (LSTM) and ARIMA-LSTM combined model. RESULTS: From 2004 to 2021, annual new cases of hepatitis C in Shandong Province increased from 635 to 5834, with a total of 61,707 cases. The incidence rate increased from 0.69/100 thousand in 2004 to 6.40/100 thousand in 2019, with a slight decrease in 2020 and 2021. The average annual incidence rate was 3.47/100 thousand. In terms of regional distribution, the hepatitis C incidence rate in Shandong Province was generally high in the west and low in the east. It is estimated that the hepatitis C incidence rate in Shandong Province will be 9.21 per 100 thousand in 2030. CONCLUSION: The hepatitis C incidence rate in Shandong Province showed an increasing trend from 2004 to 2019 and a decreasing trend in 2020 and 2021. Significant regional variations in incidence rate existed. An upward trend in incidence rate is predicted from 2022 to 2030. It is necessary to strengthen the prevention and control of hepatitis C to achieve the goal of eliminating viral hepatitis by 2030.

The interaction effects between exposure to ambient PM2.5 and economic development on the settlement intention for floating population in China.

Limited studies examined the interaction effects between exposure to ambient PM2.5 and economic development on the settlement intention of floating population. We used binary logistic model to examine the association of PM2.5, per capita GDP (PGDP), PM2.5 [Formula: see text] PGDP on the settlement intention. Additive interaction term of PM2.5 and PGDP level was used to investigate their interactive effects. Overall, each one grade increment in annual average PM2.5 was associated with decreased probability of settlement intention (OR = 0.847, 95%CI: 0.811-0.885). The interaction effect between PM2.5 and PGDP on settlement intention was significant (OR = 1.168, 95%CI: 1.142-1.194). The stratified analysis showed PM2.5 exhibits lower settlement intention in the aged 55 years or above, engaged in low-skilled works, and living in the western China. This study indicates that PM2.5-exposed will decrease the settlement intention of floating population. High economic development level can weaken the relationship between PM2.5 and settlement intention. Policymakers should balance the socio-economic development and environmental health and focus on vulnerable population.

Exploring density rectification and domain adaption method for crowd counting.

Crowd counting has received increasing attention due to its important roles in multiple fields, such as social security, commercial applications, epidemic prevention and control. To this end, we explore two critical issues that seriously affect the performance of crowd counting including nonuniform crowd density distribution and cross-domain problems. Aiming at the nonuniform crowd density distribution issue, we propose a density rectifying network (DRNet) that consists of several dual-layer pyramid fusion modules (DPFM) and a density rectification map (DRmap) auxiliary learning module. The proposed DPFM is embedded into DRNet to integrate multi-scale crowd density features through dual-layer pyramid fusion. The devised DRmap auxiliary learning module further rectifies the incorrect crowd density estimation by adaptively weighting the initial crowd density maps. With respect to the cross-domain issue, we develop a domain adaptation method of randomly cutting mixed dual-domain images, which learns domain-invariance features and decreases the domain gap between the source domain and the target domain from global and local perspectives. Experimental results indicate that the devised DRNet achieves the best mean absolute error (MAE) and competitive mean squared error (MSE) compared with other excellent methods on four benchmark datasets. Additionally, a series of cross-domain experiments are conducted to demonstrate the effectiveness of the proposed domain adaption method. Significantly, when the A and B parts of the Shanghaitech dataset are the source domain and target domain respectively, the proposed domain adaption method decreases the MAE of DRNet by 47.6 % .