Xudong Cao

Bio: Xudong Cao is an academic researcher. The author has an hindex of 1, co-authored 1 publications receiving 771 citations.

Modified SEIR and AI prediction of the epidemics trend of COVID-19 in China under public health interventions

Abstract: Background: The coronavirus disease 2019 (COVID-19) outbreak originating in Wuhan, Hubei province, China, coincided with chunyun, the period of mass migration for the annual Spring Festival. To contain its spread, China adopted unprecedented nationwide interventions on January 23 2020. These policies included large-scale quarantine, strict controls on travel and extensive monitoring of suspected cases. However, it is unknown whether these policies have had an impact on the epidemic. We sought to show how these control measures impacted the containment of the epidemic. Methods: We integrated population migration data before and after January 23 and most updated COVID-19 epidemiological data into the Susceptible-Exposed-Infectious-Removed (SEIR) model to derive the epidemic curve. We also used an artificial intelligence (AI) approach, trained on the 2003 SARS data, to predict the epidemic. Results: We found that the epidemic of China should peak by late February, showing gradual decline by end of April. A five-day delay in implementation would have increased epidemic size in mainland China three-fold. Lifting the Hubei quarantine would lead to a second epidemic peak in Hubei province in mid-March and extend the epidemic to late April, a result corroborated by the machine learning prediction. Conclusions: Our dynamic SEIR model was effective in predicting the COVID-19 epidemic peaks and sizes. The implementation of control measures on January 23 2020 was indispensable in reducing the eventual COVID-19 epidemic size.

A SIR model assumption for the spread of COVID-19 in different communities

Abstract: In this paper, we study the effectiveness of the modelling approach on the pandemic due to the spreading of the novel COVID-19 disease and develop a susceptible-infected-removed (SIR) model that provides a theoretical framework to investigate its spread within a community Here, the model is based upon the well-known susceptible-infected-removed (SIR) model with the difference that a total population is not defined or kept constant per se and the number of susceptible individuals does not decline monotonically To the contrary, as we show herein, it can be increased in surge periods! In particular, we investigate the time evolution of different populations and monitor diverse significant parameters for the spread of the disease in various communities, represented by China, South Korea, India, Australia, USA, Italy and the state of Texas in the USA The SIR model can provide us with insights and predictions of the spread of the virus in communities that the recorded data alone cannot Our work shows the importance of modelling the spread of COVID-19 by the SIR model that we propose here, as it can help to assess the impact of the disease by offering valuable predictions Our analysis takes into account data from January to June, 2020, the period that contains the data before and during the implementation of strict and control measures We propose predictions on various parameters related to the spread of COVID-19 and on the number of susceptible, infected and removed populations until September 2020 By comparing the recorded data with the data from our modelling approaches, we deduce that the spread of COVID-19 can be under control in all communities considered, if proper restrictions and strong policies are implemented to control the infection rates early from the spread of the disease

Corona Virus (COVID-19) "Infodemic" and Emerging Issues through a Data Lens: The Case of China.

Abstract: Coronavirus (COVID-19) is a humanitarian emergency, which started in Wuhan in China in early December 2019, brought into the notice of the authorities in late December, early January 2020, and, after investigation, was declared as an emergency in the third week of January 2020. The WHO declared this as Public Health Emergency of International Concern (PHEIC) on 31th of January 2020, and finally a pandemic on 11th March 2020. As of March 24th, 2020, the virus has caused a casualty of over 16,600 people worldwide with more than 380,000 people confirmed as infected by it, of which more than 10,000 cases are serious. Mainly based on Chinese newspapers, social media and other digital platform data, this paper analyzes the timeline of the key actions taken by the government and people over three months in five different phases. It found that although there was an initial delay in responding, a unique combination of strong governance, strict regulation, strong community vigilance and citizen participation, and wise use of big data and digital technologies, were some of the key factors in China's efforts to combat this virus. Being inviable and non-measurable (unlike radioactive exposure), appropriate and timely information is very important to form the basic foundation of mitigation and curative measures. Infodemic, as it is termed by WHO, is a key word, where different stakeholder's participation, along with stricter regulation, is required to reduce the impact of fake news in this information age and social media. Although different countries will need different approaches, focusing on its humanitarian nature and addressing infodemic issues are the two critical factors for future global mitigation efforts.

Predictions for COVID-19 with Deep Learning Models of LSTM, GRU and Bi-LSTM

Abstract: COVID-19, responsible of infecting billions of people and economy across the globe, requires detailed study of the trend it follows to develop adequate short-term prediction models for forecasting the number of future cases. In this perspective, it is possible to develop strategic planning in the public health system to avoid deaths as well as managing patients. In this paper, proposed forecast models comprising autoregressive integrated moving average (ARIMA), support vector regression (SVR), long shot term memory (LSTM), bidirectional long short term memory (Bi-LSTM) are assessed for time series prediction of confirmed cases, deaths and recoveries in ten major countries affected due to COVID-19. The performance of models is measured by mean absolute error, root mean square error and r2_score indices. In the majority of cases, Bi-LSTM model outperforms in terms of endorsed indices. Models ranking from good performance to the lowest in entire scenarios is Bi-LSTM, LSTM, GRU, SVR and ARIMA. Bi-LSTM generates lowest MAE and RMSE values of 0.0070 and 0.0077, respectively, for deaths in China. The best r2_score value is 0.9997 for recovered cases in China. On the basis of demonstrated robustness and enhanced prediction accuracy, Bi-LSTM can be exploited for pandemic prediction for better planning and management.