Predictive models for COVID-19 cases, deaths and recoveries in Algeria

Lounis, M.; Torrealba-Rodriguez, O.; Conde-Gutiérrez, R.A.

This study was conducted to predict the number of COVID-19 cases, deaths and recoveries using reported data by the Algerian Ministry of health from February 25, 2020 to January 10, 2021. Four models were compared including Gompertz model, logistic model, Bertalanffy model and inverse artificial neural network (ANNi). Results showed that all the models showed a good fit between the predicted and the real data (R(2)>0.97). In this study, we demonstrate that obtaining a good fit of real data is not directly related to a good prediction efficiency with future data. In predicting cases, the logistic model obtained the best precision with an error of 0.92% compared to the rest of the models studied. In deaths, the Gompertz model stood out with a minimum error of 1.14%. Finally, the ANNi model reached an error of 1.16% in the prediction of recovered cases in Algeria. .