COVID-19 Outbreak Prediction and Analysis of E-Healthcare Data Using Random Forest Algorithms

COVID-19 Outbreak Prediction and Analysis of E-Healthcare Data Using Random Forest Algorithms

Debabrata Dansana, Raghvendra Kumar, Aishik Bhattacharjee, Chandrakanta Mahanty
Copyright: © 2022 |Pages: 13
DOI: 10.4018/IJRQEH.297075
Article PDF Download
Open access articles are freely available for download

Abstract

The forecasting model used random forest algorithm. From the outcomes, it has been found that the regression models utilize basic linkage works and are exceptionally solid for forecast of COVID-19 cases in different countries as well as India. Current shared of worldwide COVID-19 confirmed case has been predicted by taking the world population and a comparatives study has been done on COVID-19 total cases growth for top 10 worst affected countries including US and excluding US. The ratio between confirmed cases vs. fatalities of COVID-19 is predicted and in the end a special study has been done on India where we have forecasted all the age groups affected by COVID-19 then we have extended our study to forecast the active, death and recovered cases especially in India and compared the situation with other countries.
Article Preview
Top

Introduction

In late December 2019, a novel coronavirus family (COVID-19) was identified by the World Health Organization (WHO) with a high degree of transmission in Wuhan, China. COVID-19 is realized by the contamination known as Severe Acute Respiratory Syndrome coronavirus 2 (SARS-CoV-2) developed by the Coronavirus Study Group of the International Committee on Taxonomy of Viruses (ICTV) (Gorbalenya et al., 2020). The starting point of this infection isnot yet affirmed; however, a sequence-based investigation recommends bats as a potential key repository (Shereen et al., 2020;Cui et al., 2019). The novel COVID-19 has been a genuine danger to public health. Strict measuresare being taken, for example, isolate, social-distancing, quarantine, physical distancing, community observation, to limit the COVID-19 episode by late February. A few sorts of COVID-19 can influence animals, and now and then, on uncommon events, COVID-19 spread animal species into the human population. The novel COVID-19 may have spread from an animal into a human. An ongoing report has indicated that once the COVID-19 flare-up begins, it will take about a month to overpower the medicinal services framework. When the clinic limit gets overwhelmed, the demise rate bounces (Conghy et al., 2020). In healthcare, an exact forecast is fundamental for the proficient administration of patients while organizing care to the needier. To help in anticipation, a few forecast models have been created utilizing different techniques and tools, including machine learning (Chen et al., 2017; Tseng et al., 2019). In the present work, the regression model is used to forecast the total number of active deaths, recovered cases around the globe in COVID-19. Predicting the total number of COVID-19 infected patients recovered is part of the dataset (https://www.kaggle.com/c/COVID19-global-forecastingweek-5/data). Deaths have occurred in several hotspot countries, including China, the United States, the United Kingdom, Italy, Germany, and others. We have addressed the current proportion of worldwide COVID-19 confirmed cases by taking the world population. We have done comparison research on COVID-19 total cases increase for the top 10 worst impacted nations, including the US and excluding the US.The ratio between confirmed cases vs fatalities of COVID-19 is predicted. The main objectives of this paper are:

  • Covid-19 affected Indian patient data analysis.

  • Forecast all the age groups affected by COVID-19.

  • Analysis to forecast the active, death, and recovered cases, especially in India.

  • Compare the situation with other countries around the globe.

Complete Article List

Search this Journal:
Reset
Volume 13: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 12: 2 Issues (2023)
Volume 11: 4 Issues (2022)
Volume 10: 4 Issues (2021)
Volume 9: 4 Issues (2020)
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing