Associations between Lifestyle Changes, Risk Perception and Anxiety during COVID-19 Lockdowns: A Case Study in Xi'an.

The outbreak of COVID-19 dramatically changed individuals' lifestyles, which in turn triggered psychological stress and anxiety. Many previous studies have discussed the relationships between lifestyle changes and anxiety and risk perception and anxiety independently. However, few papers have discussed these factors in a comprehensive and systematic manner. We established a six-dimensional system to assess changes in individuals' lifestyles, which include dietary habits, physical activity (PA), sleep, screen time, smoking and alcohol consumption, and interaction with neighbors. Then, we collected information relating to socio-demographics, lifestyle changes, risk perception, and anxiety, and discussed their associations using multilinear and stepwise logistic regressions. The results show that not all lifestyle changes had an influence on anxiety. Changes in PA and interaction with neighbors were not significantly associated with anxiety. Risk perception was found to be inversely related to anxiety. Changes in dietary habits, family harmony, and net income were negatively related to anxiety among the group with higher risk perception. As individuals perceived a higher severity of COVID-19, the impact of their financial status on anxiety increased. These findings provide a valuable resource for local governments seeking to refine their pandemic strategies by including approaches such as advocating healthy lifestyles and stabilizing the job market to improve individuals' mental health during lockdowns.

ALeRT-COVID: Attentive Lockdown-awaRe Transfer Learning for Predicting COVID-19 Pandemics in Different Countries.

Countries across the world are in different stages of COVID-19 trajectory, among which many have implemented lockdown measures to prevent its spread. Although the lockdown is effective in such prevention, it may put the economy into a depression. Predicting the epidemic progression with the government switching the lockdown on or off is critical. We propose a transfer learning approach called ALeRT-COVID using attention-based recurrent neural network (RNN) architecture to predict the epidemic trends for different countries. A source model was trained on the pre-defined source countries and then transferred to each target country. The lockdown measure was introduced to our model as a predictor and the attention mechanism was utilized to learn the different contributions of the confirmed cases in the past days to the future trend. Results demonstrated that the transfer learning strategy is helpful especially for early-stage countries. By introducing the lockdown predictor and the attention mechanism, ALeRT-COVID showed a significant improvement in the prediction performance. We predicted the confirmed cases in 1 week when extending and easing lockdown separately. Our results show that lockdown measures are still necessary for several countries. We expect our research can help different countries to make better decisions on the lockdown measures.