Comparison of an artificial neural network and Gompertz model for predicting the dynamics of deaths from COVID-19 in México

Abstract

The present work is focused on modeling and predicting the cumulative number of deaths from COVID-19 in México by comparing an artificial neural network (ANN) with a Gompertz model applying multiple optimization algorithms for the estimation of coefficients and parameters, respectively. For the modeling process, the data published by the daily technical report COVID-19 in Mexico from March 19th to September 30th were used. The data published in the month of October were included to carry out the prediction. The results show a satisfactory comparison between the real data and those obtained by both models with a R 2 > 0.999. The Levenberg–Marquardt and BFGS quasi-Newton optimization algorithm were favorable for fitting the coefficients during learning in the ANN model due to their fast and precision, respectively. On the other hand, the Nelder–Mead simplex algorithm fitted the parameters of the Gompertz model faster by minimizing the sum of squares. Therefore, the ANN model better fits the real data using ten coefficients. However, the Gompertz model using three parameters converges in less computational time. In the prediction, the inverse ANN model was solved by a genetic algorithm obtaining the best precision with a maximum error of 2.22% per day, as opposed to the 5.48% of the Gompertz model with respect to the real data reported from November 1st to 15th. Finally, according to the coefficients and parameters obtained from both models with recent data, a total of 109,724 cumulative deaths for the inverse ANN model and 100,482 cumulative deaths for the Gompertz model were predicted for the end of 2020.

Prediction of the Normalized COVID-19 Epidemic Prevention Costs of Construction Projects Based on an Optimized Neural Network

“…Based on this, neural networks and deep learning are classical methods in the prediction field, and various scientists have tried to make predictions using different methodologies. Different neural network prediction methods or models are widely used in the prediction of COVID-19 events [18][19][20][21][22][23][24]. e deep learning methods have shown promise in healthcare prediction challenges involving electrocardiogram data [25].…”

Relationship between Shale Hydration and Shale Collapse

“…An S Gompertz (SG) growth model was employed to model the damage growth. 37,38 According to the basal data, predicted values were obtained for the maximum damage (a = 1.0). A 90% confidence interval and 90% prediction interval were also determined.…”

Forecasting COVID-19 recovered cases with Artificial Neural Networks to enable designing an effective blood supply chain

“… 10 Ünlü and Namlı [ 24 ] Predicting COVID-19 confirmed cases and deaths in seven countries Confirmed cases Deaths Applying e Support Vector Machines (SVM), Holt-Winters, Facebook's Prophet, and Long-Short Term Memory (LSTM) for forecasting Using only RMSE in the interpretation of results 11 Niazkar and Niazkar [ 25 ] Estimating the confirmed cases of COVID-19 in China, Japan, Singapore, Iran, Italy, South Africa, and the United States of America. Chronological data of confirmed and death cases Applying fourteen ANN-based models to predict the COVID-19 outbreak Using a limited number of data 12 Hamadneh et al [ 26 ] Forecasting the number of total confirmed cases, total recovered cases, and total deaths in Brazil and Mexico The requested data Using ANN to estimate the number of cases of COVID-19 with prey predator algorithm (PPA) There is no comparative analysis to compare the results 13 Toga et al [ 27 ] Predicting the infected cases, the number of deaths, and the recovered cases with ARIMA and ANN in Turkey Susceptible cases Days Curfews Laboratory tests Determining the susceptible case number for each day after the first recovered case 14 Kumari and Toshniwal [ 28 ] Forecasting the COVID-19 outbreak in India with ANN Cumulative confirmed, new, and cumulative deceased cases recorded daily Utilizing a mathematical curve fitting model to understand the performance of the proposed model Not conducting a comparative analysis 15 Conde-Gutiérrez et al [ 29 ] Estimating the cumulative number of deaths from COVID-19 in México Cumulative number of deaths Comparing ANN with Gompertz model in estimating the number of deaths 16 …”