JMIR Publications

ABSTRACT

Background:

The COVID-19 pandemic infected more than 200 countries, which was recognized during December-19 from CHINA and affected more than 28 lakh people on date April 26, 2020.

Objective:

The study to identify top15 countries with spatial mapping of confirmed cases and predicted trajectories of COVID-19 next two months (until July 2, 2020) using past more than three month of data, with the most advanced Auto-Regressive Integrated Moving Average Model (ARIMA) for forecasting.

Methods:

The Auto-Regressive Integrated Moving Average Model (ARIMA) used for predicting the future data based on time-series data.Mathematical approaches are widely used to infer critical epidemiological transitions and parameters of COVID-19. Methods such as epidemic curve fitting, surveillance data during the early transmission, and other epidemic models are frequently applied to generate forecasts of COVID-19 pandemic across the world. The ARIMA model provide weight to past few values and error values to corrects it model prediction, so it better than other basic regression and exponential methods.

Results:

The analysis predicted very frightening outcomes, which defines to worsen the conditions in Iran, entire Europe, especially Italy, Spain, and France. While South Korea, after the initial blast, has come to stability, the same goes for the COVID-19 origin country China with more positive recovery cases and confirm to remain stable. The United States of America (USA) is come as a surprise and going to become the epicentre for new cases during the mid-April 2020.

Conclusions:

Based on the predictions, public health officials should tailor aggressive interventions to grasp the power exponential growth, and rapid infection control measures at hospital levels are urgently needed to curtail the COVID-19 pandemic. This study analyzed at global level and extracted data upon Machine Learning approach using Artificial intelligence techniques for top 10% or 20 countries.