Advanced Deep Learning Algorithms for Infectious Disease Modeling Using Clinical Data: A Case Study on COVID-19.

Background: Dealing with the COVID-19 pandemic has been one of the most important objectives of many countries.Intently observing the growth dynamics of the cases is one way to accomplish the solution for the pandemic.

Introduction: Infectious diseases are caused by a micro-organism/virus from another person or an animal. It causes difficulty at both the individual and collective levels. The ongoing episode of COVID-19 ailment, brought about by the new coronavirus first detected in Wuhan, China, and its quick spread far and wide revived the consideration of the world towards the impact of such plagues on an individual's everyday existence. We suggested that a basic structure be developed to work with the progressive examination of the development rate (cases/day) and development speed (cases/day2) of COVID-19 cases.

Methods: We attempt to exploit the effectiveness of advanced deep learning algorithms to predict the growth of infectious diseases based on time series data and classification based on symptoms text data and X-ray image data. The goal is to identify the nature of the phenomenon represented by the sequence of observations and forecasting.

Results: We concluded that our good habits and healthy lifestyle prevent the risk of COVID-19. We observed that by simply using masks in our daily lives, we could flatten the curve of increasing cases.Limiting human mobility resulted in a significant decrease in the development speed within a few days, a deceleration within two weeks, and a close to fixed development within six weeks.

Conclusion: These outcomes authenticate that mass social isolation is a profoundly viable measure against the spread of SARS-CoV-2, as recently recommended. Aside from the research of country- by-country predominance, the proposed structure is useful for city, state, district, and discretionary region information, serving as a resource for screening COVID-19 cases in the area.