Dataset Information

Modeling Nigerian Covid-19 cases: A comparative analysis of models and estimators.

ABSTRACT: COVID-19 remains a major pandemic currently threatening all the countries of the world. In Nigeria, there were 1, 932 COVID-19 confirmed cases, 319 discharged cases and 58 deaths as of 30th April 2020. This paper, therefore, subjected the daily cumulative reported COVID-19 cases of these three variables to nine (9) curve estimation statistical models in simple, quadratic, cubic, and quartic forms. It further identified the best of the thirty-six (36) models and used the same for prediction and forecasting purposes. The data collected by the Nigeria Centre for Disease Control for sixty-four (64) days, two (2) months and three (3), were daily monitored and eventually analyzed. We identified the best models to be Quartic Linear Regression Model with an autocorrelated error of order 1 (AR(1)); and found the Ordinary Least Squares, Cochrane Orcutt, Hildreth-Lu, and Prais-Winsten and Least Absolute Deviation (LAD) estimators useful to estimate the models' parameters. Consequently, we recommended the daily cumulative forecast values of the LAD estimator for May and June 2020 with a 99% confidence level. The forecast values are alarming, and so, the Nigerian Government needs to hastily review her activities and interventions towards COVID-19 to provide some tactical and robust structures and measures to avert these challenges.

SUBMITTER: Ayinde K

PROVIDER: S-EPMC7282783 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Modeling Nigerian Covid-19 cases: A comparative analysis of models and estimators.

Ayinde Kayode K Lukman Adewale F AF Rauf Rauf I RI Alabi Olusegun O OO Okon Charles E CE Ayinde Opeyemi E OE

Chaos, solitons, and fractals 20200609

COVID-19 remains a major pandemic currently threatening all the countries of the world. In Nigeria, there were 1, 932 COVID-19 confirmed cases, 319 discharged cases and 58 deaths as of 30th April 2020. This paper, therefore, subjected the daily cumulative reported COVID-19 cases of these three variables to nine (9) curve estimation statistical models in simple, quadratic, cubic, and quartic forms. It further identified the best of the thirty-six (36) models and used the same for prediction and f ...[more]

PMID: 32536757

Similar Datasets

Project description:BackgroundCoronaviruses are a group of viruses that belong to the Family Coronaviridae, genus Betacoronavirus. In December 2019, a new coronavirus disease (COVID-19) characterized by severe respiratory symptoms was discovered. The causative pathogen was a novel coronavirus known as 2019-nCoV and later as SARS-CoV-2. Within two months of its discovery, COVID-19 became a pandemic causing widespread morbidity and mortality.MethodologyWhole genome sequence data of SARS-CoV-2 isolated from Nigerian COVID-19 cases were retrieved by downloading from GISAID database. A total of 18 sequences that satisfied quality assurance (length ≥29,700 nts and number of unknown bases denoted as "N" ≤ 5%) were used for the study. In addition, genome sequence of SARS-CoV-2 obtained from Nigeria's COVID-19 index case (Accession ID: EPI_ISL_413550) and the reference genome (Accession NC_ 045512.2) were obtained from GISAID and the GenBank databases, respectively. Multiple sequence alignment (MSA) was done in MAFFT (Version 7.471) while SNP calling was implemented in DnaSP (Version 6.12.03), respectively and then visualized in Jalview (Version 2.11.1.0). Phylogenetic analysis was with MEGA X software.ResultsNigerian SARS-CoV-2 had 99.9% genomic similarity with four large conserved genomic regions. A total of 66 SNPs were identified out of which 31 were informative. Nucleotide diversity assessment gave Pi = 0.00048 and average SNP frequency of 2.22 SNPs per 1000 nts. Non-coding genomic regions particularly 5'UTR and 3'UTR had a SNP density of 3.77 and 35.4, respectively. The region with the highest SNP density was ORF10 with a frequency of 8.55 SNPs/1000 nts). This value was significantly higher (P < 0.01) than that of the spike gene, the region of greatest interest in SARS-CoV-2 genomics. Majority (72.2%) of viruses in Nigeria are of L lineage with preponderance of D614G mutation which accounted for 11 (61.1%) out of the 18 viral sequences. Nigeria SARS-CoV-2 revealed 3 major clades namely Oyo, Ekiti and Osun on a maximum likelihood phylogenetic tree.Conclusion and recommendationThere was a preponderance of L lineage (to include the new lineage scheme) and D614G mutants. Nigerian SARS-CoV-2 genome revealed ORF1ab as the region containing the highest SNP density as compared to the spike gene. The implication of this distribution of SNPs for the empirical lower infectivity of SARS-CoV-2 in Nigeria is discussed. This also underscores the need for more aggressive testing and treatment of COVID-19 in Nigeria. Additionally, attempt to produce testing kits for COVID-19 in Nigeria should consider the conserved regions identified in this study. Strict adherence to COVID-19 preventive measure is recommended in view of Nigerian SARS-CoV-2 phylogenetic clustering pattern, which suggests intensive community transmission possibly rooted in communal culture characteristic of many ethnicities in Nigeria.

Project description:BackgroundMonkeypox virus is gaining attention due to its severity and spread among people. This study sheds light on the modeling and forecasting of new monkeypox cases. Knowledge about the future situation of the virus using a more accurate time series and stochastic models is required for future actions and plans to cope with the challenge.MethodsWe conduct a side-by-side comparison of the machine learning approach with the traditional time series model. The multilayer perceptron model (MLP), a machine learning technique, and the Box-Jenkins methodology, also known as the ARIMA model, are used for classical modeling. Both methods are applied to the Monkeypox cumulative data set and compared using different model selection criteria such as root mean square error, mean square error, mean absolute error, and mean absolute percentage error.ResultsWith a root mean square error of 150.78, the monkeypox series follows the ARIMA (7,1,7) model among the other potential models. Comparatively, we use the multilayer perceptron (MLP) model, which employs the sigmoid activation function and has a different number of hidden neurons in a single hidden layer. The root mean square error of the MLP model, which uses a single input and ten hidden neurons, is 54.40, significantly lower than that of the ARIMA model. The actual confirmed cases versus estimated or fitted plots also demonstrate that the multilayer perceptron model has a better fit for the monkeypox data than the ARIMA model.Conclusions and recommendationWhen it comes to predicting monkeypox, the machine learning method outperforms the traditional time series. A better match can be achieved in future studies by applying the extreme learning machine model (ELM), support vector machine (SVM), and some other methods with various activation functions. It is thus concluded that the selected data provide a real picture of the virus. If the situations remain the same, governments and other stockholders should ensure the follow-up of Standard Operating Procedures (SOPs) among the masses, as the trends will continue rising in the upcoming 10 days. However, governments should take some serious interventions to cope with the virus.LimitationIn the ARIMA models selected for forecasting, we did not incorporate the effect of covariates such as the effect of net migration of monkeypox virus patients, government interventions, etc.

Dataset Information

Modeling Nigerian Covid-19 cases: A comparative analysis of models and estimators.

Publications

Modeling Nigerian Covid-19 cases: A comparative analysis of models and estimators.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets