Dataset Information

Stochastic modelling for predicting COVID-19 prevalence in East Africa Countries.

ABSTRACT: Coronavirus (COVID-19) has continued to be a global threat to public health. As the matter of fact, it needs unreserved effort to monitor the prevalence of the virus. However, applying an effective prediction of the prevalence is thought to be the fundamental requirement to effectively control the spreading rate. Time series models have extensively been considered as the convenient methods to predict the prevalence or spreading rate of the disease. This study, therefore, aimed to apply the Autoregressive Integrated Moving Average (ARIMA) modeling approach for projecting coronavirus (COVID-19) prevalence patterns in East Africa Countries, mainly Ethiopia, Djibouti, Sudan and Somalia. The data for the study were obtained from the reports of confirmed COVID-19 cases by the official website of Johns Hopkins University from 13th March, 2020 to 30th June, 2020.The results of the study, then, showed that in the coming four month, the number of COVID-19 positive people in Ethiopia may reach up to 56,610 from 5,846 on June 30, 2020 in average-rate scenario. However, in worst case scenario forecast, the model showed that the cases will be around 84,497. The analysis further depicted that with average interventions and control scenario, cumulative number of infected persons in Djibouti, Somalia and Sudan will increase from 4,656, 2,904 and 9,258 respectively at the end of June to 8,336, 3,961 and 21,388, which is by the end of October, 2020, after four-months. But, with insufficient intervention, the number of infected persons may grow quickly and reach up to 14,072, 10,037 and 38,174 in Djibouti, Somalia and Sudan respectively. Generally, the extent of the coronavirus spreading was increased from time to time in the past four month, until 30 th June, 2020, and it is expected to continue quicker than before for the coming 4-month, until the end of October, 2020, in Ethiopia, Djibouti, Somalia, and Sudan and more rapidly than before in Sudan and Ethiopia, while the peak will remain unknown yet. Therefore, an effective implementation of the preventive measures and a rigorous compliance by avoiding negligence with the rules such as prohibiting public gatherings, travel restrictions, personal protection measures, and social distancing may alleviate the spreading rates of the virus, particularly, Sudan and Ethiopia. Moreover, more efforts should be exerted on Ethiopian side to control the population movement across all the border areas and to strengthen border quarantining. Further, through updating more new data with continuous reconsideration of predictive model, provide useful and more precise prediction. Applying, ARIMAX-Transfer Function model in region-wise by take in to consideration of climatic data like temperature and humidity in each countries looking spatial pattern for reliable measure of COVID-19 prevalence.

SUBMITTER: Takele R

PROVIDER: S-EPMC7434383 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:The worldwide coronavirus (COVID-19) pandemic made dramatic and rapid progress in the year 2020 and requires urgent global effort to accelerate the development of a vaccine to stop the daily infections and deaths. Several types of vaccine have been designed to teach the immune system how to fight off certain kinds of pathogens. mRNA vaccines are the most important candidate vaccines because of their capacity for rapid development, high potency, safe administration and potential for low-cost manufacture. mRNA vaccine acts by training the body to recognize and response to the proteins produced by disease-causing organisms such as viruses or bacteria. This type of vaccine is the fastest candidate to treat COVID-19 but it currently facing several limitations. In particular, it is a challenge to design stable mRNA molecules because of the inefficient in vivo delivery of mRNA, its tendency for spontaneous degradation and low protein expression levels. This work designed and implemented a sequence deep model based on bidirectional GRU and LSTM models applied on the Stanford COVID-19 mRNA vaccine dataset to predict the mRNA sequences responsible for degradation by predicting five reactivity values for every position in the sequence. Four of these values determine the likelihood of degradation with/without magnesium at high pH (pH 10) and high temperature (50 degrees Celsius) and the fifth reactivity value is used to determine the likely secondary structure of the RNA sample. The model relies on two types of features, namely numerical and categorical features, where the categorical features are extracted from the mRNA sequences, structure and predicted loop. These features are represented and encoded by numbers, and then, the features are extracted using embedding layer learning. There are five numerical features depending on the likelihood for each pair of nucleotides in the RNA. The model gives promising results because it predicts the five reactivity values with a validation mean columnwise root mean square error (MCRMSE) of 0.125 using LSTM model with augmentation and the codon encoding method. Codon encoding outperforms Base encoding in MCRMSE validation error using the LSTM model meanwhile Base encoding outperforms codon encoding due to less over-fitting and the difference between the training and validation loss error is 0.008.

Project description:BackgroundThe Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) was first detected in China at the end of 2019 and it has since spread in few months all over the World. Italy was one of the first Western countries who faced the health emergency and is one of the countries most severely affected by the pandemic. The diffusion of Coronavirus disease 2019 (COVID-19) in Italy has followed a peculiar spatial pattern, however the attention of the scientific community has so far focussed almost exclusively on the prediction of the evolution of the disease over time.MethodsOfficial freely available data about the number of infected at the finest possible level of spatial areal aggregation (Italian provinces) are used to model the spatio-temporal distribution of COVID-19 infections at local level. An endemic-epidemic time-series mixed-effects generalized linear model for areal disease counts has been implemented to understand and predict spatio-temporal diffusion of the phenomenon.ResultsThree subcomponents characterize the fitted model. The first describes the transmission of the illness within provinces; the second accounts for the transmission between nearby provinces; the third is related to the evolution of the disease over time. At the local level, the provinces first concerned by containment measures are those that are not affected by the effects of spatial neighbours. On the other hand, the component accounting for the spatial interaction with surrounding areas is prevalent for provinces that are strongly involved by contagions. Moreover, the proposed model provides good forecasts for the number of infections at local level while controlling for delayed reporting.ConclusionsA strong evidence is found that strict control measures implemented in some provinces efficiently break contagions and limit the spread to nearby areas. While containment policies may potentially be more effective if planned considering the peculiarities of local territories, the effective and homogeneous enforcement of control measures at national level is needed to prevent the disease control being delayed or missed as a whole. This may also apply at international level where, as it is for the European Union or the United States, the internal border checks among states have largely been abolished.

Project description:BackgroundRecurring COVID-19 waves highlight the need for tools able to quantify transmission risk, and identify geographical areas at risk of outbreaks. Local outbreak risk depends on complex immunity patterns resulting from previous infections, vaccination, waning and immune escape, alongside other factors (population density, social contact patterns). Immunity patterns are spatially and demographically heterogeneous, and are challenging to capture in country-level forecast models.MethodsWe used a spatiotemporal regression model to forecast subnational case and death counts and applied it to three EU countries as test cases: France, Czechia, and Italy. Cases in local regions arise from importations or local transmission. Our model produces age-stratified forecasts given age-stratified data, and links reported case counts to routinely collected covariates (e.g. test number, vaccine coverage). We assessed the predictive performance of our model up to four weeks ahead using proper scoring rules and compared it to the European COVID-19 Forecast Hub ensemble model. Using simulations, we evaluated the impact of variations in transmission on the forecasts. We developed an open-source RShiny App to visualise the forecasts and scenarios.ResultsAt a national level, the median relative difference between our median weekly case forecasts and the data up to four weeks ahead was 25% (IQR: 12-50%) over the prediction period. The accuracy decreased as the forecast horizon increased (on average 24% increase in the median ranked probability score per added week), while the accuracy of death forecasts was more stable. Beyond two weeks, the model generated a narrow range of likely transmission dynamics. The median national case forecasts showed similar accuracy to forecasts from the European COVID-19 Forecast Hub ensemble model, but the prediction interval was narrower in our model. Generating forecasts under alternative transmission scenarios was therefore key to capturing the range of possible short-term transmission dynamics.DiscussionOur model captures changes in local COVID-19 outbreak dynamics, and enables quantification of short-term transmission risk at a subnational level. The outputs of the model improve our ability to identify areas where outbreaks are most likely, and are available to a wide range of public health professionals through the Shiny App we developed.

Dataset Information

Stochastic modelling for predicting COVID-19 prevalence in East Africa Countries.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets