Spatio-temporal prediction of the COVID-19 pandemic in US counties: modeling with a deep LSTM neural network.

Prediction of complex epidemiological systems such as COVID-19 is challenging on many grounds. Commonly used compartmental models struggle to handle an epidemiological process that evolves rapidly and is spatially heterogeneous. On the other hand, machine learning methods are limited at the beginning of the pandemics due to small data size for training. We propose a deep learning approach to predict future COVID-19 infection cases and deaths 1 to 4 weeks ahead at the fine granularity of US counties. The multi-variate Long Short-term Memory (LSTM) recurrent neural network is trained on multiple time series samples at the same time, including a mobility series. Results show that adding mobility as a variable and using multiple samples to train the network improve predictive performance both in terms of bias and of variance of the forecasts. We also show that the predicted results have similar accuracy and spatial patterns with a standard ensemble model used as benchmark. The model is attractive in many respects, including the fine geographic granularity of predictions and great predictive performance several weeks ahead. Furthermore, data requirement and computational intensity are reduced by substituting a single model to multiple models folded in an ensemble model.

Socioeconomic factors analysis for COVID-19 US reopening sentiment with Twitter and census data.

Investigating and classifying sentiments of social media users (e.g., positive, negative) towards an item, situation, and system are very popular among researchers. However, they rarely discuss the underlying socioeconomic factor associations for such sentiments. This study attempts to explore the factors associated with positive and negative sentiments of the people about reopening the economy, in the United States (US) amidst the COVID-19 global crisis. It takes into consideration the situational uncertainties (i.e., changes in work and travel patterns due to lockdown policies), economic downturn and associated trauma, and emotional factors such as depression. To understand the sentiment of the people about the reopening economy, Twitter data was collected, representing the 50 States of the US and Washington D.C, the capital city of the US. State-wide socioeconomic characteristics of the people (e.g., education, income, family size, and employment status), built environment data (e.g., population density), and the number of COVID-19 related cases were collected and integrated with Twitter data to perform the analysis. A binary logit model was used to identify the factors that influence people toward a positive or negative sentiment. The results from the logit model demonstrate that family households, people with low education levels, people in the labor force, low-income people, and people with higher house rent are more interested in reopening the economy. In contrast, households with a high number of family members and high income are less interested in reopening the economy. The accuracy of the model is reasonable (i.e., the model can correctly classify 56.18% of the sentiments). The Pearson chi-squared test indicates that this model has high goodness-of-fit. This study provides clear insights for public and corporate policymakers on potential areas to allocate resources, and directional guidance on potential policy options they can undertake to improve socioeconomic conditions, to mitigate the impact of pandemic in the current situation, and in the future as well.

Vascular Surgery Practice Guidelines during COVID-19 Pandemic in a Setting of High Work Volume Against Limited Resources: Perspective of a Developing Country.

BACKGROUND: The situation of coronavirus disease 2019 (COVID-19) pandemic in the Indian subcontinent is worsening. In Bangladesh, rate of new infection has been on the rise despite limited testing facility. Constraint of resources in the health care sector makes the fight against COVID-19 more challenging for a developing country like Bangladesh. Vascular surgeons find themselves in a precarious situation while delivering professional services during this crisis. With the limited number of dedicated vascular surgeons in Bangladesh, it is important to safeguard these professionals without compromising emergency vascular care services in the long term. To this end, we at the National Institute of Cardiovascular Diseases and Hospital, Dhaka, have developed a working guideline for our vascular surgeons to follow during the COVID-19 pandemic. The guideline takes into account high vascular work volume against limited resources in the country. METHODS: A total of 307 emergency vascular patients were dealt with in the first 4 COVID-19 months (March through June 2020) according to the working guideline, and the results were compared with the 4 pre-COVID-19 months. Vascular trauma, dialysis access complications, and chronic limb-threatening ischemia formed the main bulk of the patient population. Vascular health care workers were regularly screened for COVID-19 infection. RESULTS: There was a 38% decrease in the number of patients in the COVID-19 period. Treatment outcome in COVID-19 months were comparable with that in the pre-COVID-19 months except that limb loss in the chronic limb-threatening ischemia patients was higher. COVID-19 infection among the vascular health care professionals was low. CONCLUSIONS: Vascular surgery practice guidelines customized for the high work volume and limited resources of the National Institute of Cardiovascular Diseases and Hospital, Dhaka were effective in delivering emergency care during COVID-19 pandemic, ensuring safety of the caregivers. Despite the fact that similar guidelines exist in different parts of the world, we believe that the present one is still relevant on the premises of a deepening COVID-19 crisis in a developing country like Bangladesh.