Time Series Forecasting of COVID-19 Mortality in SADC region with Facebook Prophet Model

This study proposes Facebook-Prophet model for understanding and forecasting of corona virus (COVID-19) mortality in Southern African Development Community (SADC) region over a 90-day time period. Findings showed that COVID-19 mortality in SADC region is expected to degrade in the near future. Model performance metrics were used to compute prediction performance. These results implied that the selected model was satisfactory and reliable. Findings of the study are expected to raise situational awareness into better understanding of the pandemic and to provide support for strategic health decisions for better management of COVID-19 disease. Moreover, the study provides a series of recommendations to be followed in order to decline COVID-19 related deaths in SADC countries. © 2022 IEEE.

Application of Predictive Analytics for Early Warning System for Healthcare Management

Coronavirus disease (COVID-19) has become a pandemic after its outbreak in January 2020. The majority of the countries have witnessed peak effects of the disease, and they need to learn from their past experience of dealing with and pro-actively controlling the future waves. Thus, this article aims to analyse the effect of the COVID-19 pandemic on some of the key states in India and provide analytical actionable insight for better epidemic management. In this article, we have focused on Maharashtra and tried to show how other states can also incorporate pro-active pandemic management to reduce the number of causalities in the following waves. The key objectives of this article are to provide a scenario base forecasted number of patients for Maharashtra with sufficient lead time, review the current capacity of the health infrastructure, analyse the risk of the current health infrastructure, identify the breaking point of system failure in advance, measure the gap between capacity (supply) vs demand and raise alarms and device an early warning system (EWS) pro-actively. Quantitative analysis of the statistics related to COVID-19 has been done based on their official (government) data and some of the previous research work. Prophet Model has been used to forecast and then the forecasted values are combined with the daily load in hospitals to measure the extra load on the healthcare system.

COVID 19 Prediction Model Using Prophet Forecasting with Solution for Controlling Cases and Economy

Coronavirus disease outbreak (COVID-19) has threatened the entire world and has made lives difficult. It has drastically affected the way of living, working, and managing routines for the human beings, by living indoors. In a country like India, with a population of about 1.35 billion, the virus is spreading so fast that the control has become unmanageable. This paper presents COVID 19 data analysis and the prediction model that helps plan and organize things as precautionary measures. In this chapter, analysis is performed on COVID 19 data, and the prediction model is proposed for October. The analysis and prediction is performed using two methods, viz. random forest and time series. The chapter also compared the analyzed results. The idea behind analyzing the available dataset and the comparison of two prediction models is to supply some solutions to control the spreading of COVID 19. In this chapter, analysis is presented state-wise and country wise for the active number of cases and the date cases. Recovery rates are also analyzed. Gender-specific detailed analysis is also presented in this chapter with different age groups in India.

Machine learning modeling techniques and statistical projections to predict the outbreak of COVID-19 with implication to India

The World Health Organization confirmed coronavirus as global pandemic on March 11, 2020. The first wave started during March–April 2020, followed by second wave during September–November 2020 and third wave during January–February 2021 in many parts of the world. In spite of vaccinations and herd immunity, the new mutating virus is continuously inducing new spikes and asymptotic death rates in several countries. Various prediction models are used to predict the outcomes of pandemic. Machine learning regression models such as Least Absolute Shrinkage and Selection Operator (Lasso), Linear Regression, Ridge, Elastic-Net, Random Forest, Adaptive Boosting (AdaBoost), Light Gradient Boosted Machine (LGBM), and Extreme Gradient Boosting (XGBoost) are considered to predict and study the exponential increase of mortality rate, number of confirmed cases, and recovery rate. Also, Facebook Prophet Model is used to predict the outbreak of COVID-19. To build these models, COVID-19 real-time dataset is extracted from Johns Hopkins University that considers the number of confirmed cases, total deaths, and number of recovered cases. Information such as country/region, confirmed cases, province/state, recovered cases, death rate, and last update is considered to make predictions. These models were trained, tested, and compared for their performances based on the parameters R-squared value, R-squared modified score, Mean Squared deviation and Root Mean Square Error. The results are tabulated to observe the best model for pandemic outbreak prediction. Based on the results of these models, the concerned officials can infer the necessary measure that has to be taken to control the outbreak of COVID-19 pandemic. © 2022 Elsevier Inc. All rights reserved.

Forecasting the coronavirus disease 2019 pandemic in India using machine learning and statistical models

COVID-19, which is an infectious disease caused by the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has resulted in a massive blow to India with respect to the health of its citizens and economy. The work in this paper focuses on the Prophet model, linear regression model, Holt's model and the ARIMA model for predicting the number of confirmed, recovered cases, deaths and active cases along with growth rate, recovery rate and mortality rate in India for the month of November 2020. The performance of all the above mentioned models has been evaluated using standard metrics namely R2, adjusted R2, root-mean-square error and mean absolute error. © 2022 Inderscience Enterprises Ltd.

COVID-19 Cases in India: Prediction and Analysis using Machine Learning

The coronavirus may have been a family of viruses that may be causing an unhealthiest, which may vary from an unwellness and cough to a typically additional severe disease. SARS-CoV-2 is a distinct coronavirus familial infection that was first found in 2019 and has never been seen in humans previously. It is a cumulative virus that began in Wuhan at the end of the year 2019 (December). Because of the rapid pace of spread around the continent, the World Health Organization labeled it a global epidemic. The main purpose of this study is to find out the analysis and forecasting of the third wave of COVID-19 in India. We predicted that the number of instances will rise in the next four months, peaking in October. For time series forecasting, we employed the ARIMA and Prophet model, which is the most often used forecasting technique. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

A Combined Model of SARIMA and Prophet Models in Forecasting AIDS Incidence in Henan Province, China.

Acquired immune deficiency syndrome (AIDS) is a serious public health problem. This study aims to establish a combined model of seasonal autoregressive integrated moving average (SARIMA) and Prophet models based on an L1-norm to predict the incidence of AIDS in Henan province, China. The monthly incidences of AIDS in Henan province from 2012 to 2020 were obtained from the Health Commission of Henan Province. A SARIMA model, a Prophet model, and two combined models were adopted to fit the monthly incidence of AIDS using the data from January 2012 to December 2019. The data from January 2020 to December 2020 was used to verify. The mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) were used to compare the prediction effect among the models. The results showed that the monthly incidence fluctuated from 0.05 to 0.50 per 100,000 individuals, and the monthly incidence of AIDS had a certain periodicity in Henan province. In addition, the prediction effect of the Prophet model was better than SARIMA model, the combined model was better than the single models, and the combined model based on the L1-norm had the best effect values (MSE = 0.0056, MAE = 0.0553, MAPE = 43.5337). This indicated that, compared with the L2-norm, the L1-norm improved the prediction accuracy of the combined model. The combined model of SARIMA and Prophet based on the L1-norm is a suitable method to predict the incidence of AIDS in Henan. Our findings can provide theoretical evidence for the government to formulate policies regarding AIDS prevention.

An infodemiological framework for tracking the spread of SARS-CoV-2 using integrated public data.

The outbreak of the SARS-CoV-2 novel coronavirus has caused a health crisis of immeasurable magnitude. Signals from heterogeneous public data sources could serve as early predictors for infection waves of the pandemic, particularly in its early phases, when infection data was scarce. In this article, we characterize temporal pandemic indicators by leveraging an integrated set of public data and apply them to a Prophet model to predict COVID-19 trends. An effective natural language processing pipeline was first built to extract time-series signals of specific articles from a news corpus. Bursts of these temporal signals were further identified with Kleinberg's burst detection algorithm. Across different US states, correlations for Google Trends of COVID-19 related terms, COVID-19 news volume, and publicly available wastewater SARS-CoV-2 measurements with weekly COVID-19 case numbers were generally high with lags ranging from 0 to 3 weeks, indicating them as strong predictors of viral spread. Incorporating time-series signals of these effective predictors significantly improved the performance of the Prophet model, which was able to predict the COVID-19 case numbers between one and two weeks with average mean absolute error rates of 0.38 and 0.46 respectively across different states.

Ensemble Model to Forecast the End of the Covid-19 Pandemic

The coronavirus disease 2019 (Covid-19) epidemic has caused a worldwide health catastrophe that has had a profound influence on how we see our planet and our daily lives. In this pandemic circumstance, machine learning (ML) based prediction models demonstrate their value in predicting perioperative outcomes to enhance decision-making on future course of action. Ensemble learning is used in the majority of ML based forecasting approaches. The ML models anticipate the number of patients who will be affected by Covid-19, and use this information to forecast the end of the pandemic is to be leveraged. Three types of predictions are made: the number of newly infected cases, the number of deaths, and the number of recoveries in the next ‘x’ number of days. By combining one of the forecasting models with classifiers, we can predict the end of the pandemic. The proposed idea combines the SIRF model from epidemiology and a forecasting machine learning model named Prophet and a Naïve Bayes Classifier to predict the end of the pandemic. Using the theoretical equations of the SIRF model, we developed a formula for infectious growth rate. The classifier uses this infectious growth rate to check if the infection is fading. With confirmed, recovered and fatalities data, the infectious growth rate is calculated. Naïve Bayes classifier is used to check if the pandemic is about to end or not. If not then forecast the data for ‘x’ number of days and do the calculations again. The process continues until we get a time frame where the pandemic may reach its end. The results are discussed for 2 countries India and Israel. The forecasts done for Israel were very accurate to the actual data, whilst for India it was less comparatively as India was hit by 2 waves of Covid-19 pandemic. By leveraging the forecasting and classification capabilities of machine learning models like FBProphet, Naïve Bayes Classifier, and the mathematical equations of the SIRF model from epidemiology, the life span of the pandemic is determined. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Acceleration of opioid-related EMS runs in the spring of 2020: The National Emergency Medical Services Information System data for 2018-2020.

BACKGROUND: State- and county-level reports suggest that the COVID-19 pandemic exacerbated the opioid crisis. We examined US national trends of nonfatal opioid overdose in 2020 in comparison to pre-COVID years 2018-2019. METHODS: We used National Emergency Medical Services Information System (NEMSIS) data to conduct a temporal analysis from 2018 to 2020. Opioid-related EMS run was defined using five scenarios of naloxone administration. To determine annual patterns and slope inflection points, we used the Prophet model of the time series analysis. Linear slopes and their 95% confidence intervals (CIs) were calculated for pre-stay-at-home (pre-SaH) and SaH periods in 2020 and compared to the slopes during the same time in 2018-2019. Three cut-points for SaH start were considered: March 19, 24, and 29. RESULTS: We identified 91,065, 144,802, and 242,904 opioid-related EMS runs in 2018-2020, respectively. In 2020, opioid-related runs increased in January-June, with a pronounced acceleration in March, which coincides with the stay-at-home (SaH) orders. In both 2018 and 2019, opioid-related runs increased in January-August without the spring acceleration. In 2020, weekly increases (95% CI) during SaH for all examined cut-points were significantly greater than in pre-SaH: 18.09 (16.03-20.16) vs. 6.44 (3.42-9.47) for March 19, 17.77 (15.57-19.98) vs. 4.85 (2.07-7.64) for March 24, 18.03 (15.68-20.39) vs. 4.97(2.4-7.54) for March 29. No significant difference was found between these periods in 2018-2019. CONCLUSIONS: The acceleration of opioid-related EMS runs during the SaH period of 2020 suggests that EMS data may serve as an early warning system for local health jurisdictions to deploy harm reduction/prevention resources.

Intelligent computing on time-series data analysis and prediction of COVID-19 pandemics.

Covid-19 disease caused by novel coronavirus (SARS-CoV-2) is a highly contagious epidemic that originated in Wuhan, Hubei Province of China in late December 2019. World Health Organization (WHO) declared Covid-19 as a pandemic on 12th March 2020. Researchers and policy makers are designing strategies to control the pandemic in order to minimize its impact on human health and economy round the clock. The SARS-CoV-2 virus transmits mostly through respiratory droplets and through contaminated surfacesin human body.Securing an appropriate level of safety during the pandemic situation is a highly problematic issue which resulted from the transportation sector which has been hit hard by COVID-19. This paper focuses on developing an intelligent computing model for forecasting the outbreak of COVID-19. The Facebook Prophet model predicts 90 days future values including the peak date of the confirmed cases of COVID-19 for six worst hit countries of the world including India and six high incidence states of India. The model also identifies five significant changepoints in the growth curve of confirmed cases of India which indicate the impact of the interventions imposed by Government of India on the growth rate of the infection. The goodness-of-fit of the model measures 85% MAPE for all six countries and all six states of India. The above computational analysis may be able to throw some light on planning and management of healthcare system and infrastructure.

An Eye on the Future of COVID-19: Prediction of Likely Positive Cases and Fatality in India over a 30-Day Horizon Using the Prophet Model.

OBJECTIVE: The coronavirus disease (COVID-19) pandemic was initiated in Wuhan Province of mainland China in December 2019 and has spread over the world. This study analyzes the effects of COVID-19 based on likely positive cases and fatality in India during and after the lockdown period from March 24, 2020, to May 24, 2020. METHODS: Python has been used as the main programming language for data analysis and forecasting using the Prophet model, a time series analysis model. The data set has been preprocessed by grouping together the days for total numbers of cases and deaths on few selected dates and removing missing values present in some states. RESULTS: The Prophet model performs better in terms of precision on the real data. Prediction depicts that, during the lockdown, the total cases were rising but in a controlled manner with an accuracy of 87%. After the relaxation of lockdown rules, the predictions have shown an obstreperous situation with an accuracy of 60%. CONCLUSION: The resilience could have been better if the lockdown with strict norms was continued without much relaxation. The situation after lockdown has been found to be uncertain as observed by the experimental study conducted in this work.