Attributable Fraction and Forecasting for COVID-19 Confirmed Cases in Nigeria Using Facebook- Prophet Machine Learning Model

Abstract

Aims: The motivation is to know the attributable fraction among Nigerians who tested positive for covid-19 and forecast the covid-19 cases.
 Place and Duration of Study: We extracted data from (https://covid19.ncdc.gov.ng/) on 8th September,2021 and covid.19analytics package on 7th September, 2021, from Data Repository by Johns Hopkins University Center for Systems Science and Engineering , Status of Cases in Toronto – City of Toronto , COVID-19: Open Data Toronto ,COVID-19: Health Canada , Severe acute respiratory syndrome coronavirus 2 isolate Wuhan-Hu-1, COViD-19 Vaccination and Testing records from “Our World In Data” and Pandemics historical records from Visual Capitalist. Data in Nigeria contained the number of samples tested, confirmed cases, active cases, discharged cases and deaths.
 Methodology: Attributable fraction was used to compute the proportion of patients who tested positive to Covid-19. By using the time for regressor, Prophet model will fit many non-linear and linear functions of time components. Prophet uses the Fourier series to get flexible model to forecast and fit the seasonality effects. A fast solution for L-BFGS which stands for Limited memory Broyden-Fletcher-Goldfarb-Shannon algorithm, is used with Stan backend for the prediction problem.
 Results: As at Saturday 11th September 2021,7:18am Nigeria local time, a total of 2884034 samples have been tested for covid-19, with 198239 confirmed cases,9871 active cases,185780 discharged cases and 2588 deaths. The attributable fraction for covid-19 in Nigeria was 0.0687. The r square is very high (0.999), and the p value is very low (2.2e-16).
 Conclusion: The attributable fraction gives the percentage of the patients who tested positive to covid-19, among the 2884034 samples tested. It implies that the remaining percentage of patients who tested negative to covid-19 only exhibit covid-19 symptoms or were exposed to the virus. The confirmed cases were found to be highest on Saturdays with the lowest on Tuesdays.

The dynamics of hybrid-immune and immunodeficient susceptible individuals and the three stages of COVID-19 vaccination

“…The need to capture in a model the dynamics of the spread of COVID-19 virus in order to appropriately predict and curb its future anticipated variants (a variant is where the virus contains at least one new change to the original virus and sometimes variants of the virus may develop [11]) or second waves has led to the proposal of variety of models, both new and modification of existing ones. Ibidoja and Fowobaje [12] extracted COVID-19 data from the Nigerian Center for Disease and Control (NCDC) repository to forecast and fit the trend of the virus. When it comes to modeling the spread of infectious diseases, the compartmental models are the general modeling techniques adopted by researchers [13].…”