tetano
Editor, Senior Moderator
PLoS One
. 2023 Mar 24;18(3):e0263991.
doi: 10.1371/journal.pone.0263991. eCollection 2023.
Neo-epidemiological machine learning based method for COVID-19 related estimations
Mouhamad Bodaghie[SUP] 1 [/SUP], Farnaz Mahan[SUP] 1 [/SUP], Leyla Sahebi[SUP] 2 [/SUP], Hossein Dalili[SUP] 3 [/SUP]
Affiliations
Abstract
The 2019 newfound Coronavirus (COVID-19) still remains as a threatening disease of which new cases are being reported daily from all over the world. The present study aimed at estimating the related rates of morbidity, growth, and mortality for COVID-19 over a three-month period starting from Feb, 19, 2020 to May 18, 2020 in Iran. In addition, it revealed the effect of the mean age, changes in weather temperature and country's executive policies including social distancing, restrictions on travel, closing public places, shops and educational centers. We have developed a combined neural network to estimate basic reproduction number, growth, and mortality rates of COVID-19. Required data was obtained from daily reports of World Health Organization (WHO), Iran Meteorological Organization (IRIMO) and the Statistics Center of Iran. The technique used in the study encompassed the use of Artificial Neural Network (ANN) combined with Swarm Optimization (PSO) and Bus Transportation Algorithms (BTA). The results of the present study showed that the related mortality rate of COVID-19 is in the range of [0.1], and the point 0.275 as the mortality rate provided the best results in terms of the total training and test squared errors of the network. Furthermore, the value of basic reproduction number for ANN-BTA and ANN-PSO was 1.045 and 1.065, respectively. In the present study, regarding the closest number to the regression line (0.275), the number of patients was equal to 2566200 cases (with and without clinical symptoms) and the growth rate based on arithmetic means was estimated to be 1.0411 and 1.06911, respectively. Reviewing the growth and mortality rates over the course of 90 days, after 45 days of first case detection, the highest increase in mortality rate was reported 158 cases. Also, the highest growth rate was related to the eighth and the eighteenth days after the first case report (2.33). In the present study, the weather variant in relationship to the basic reproduction number and mortality rate was estimated ineffective. In addition, the role of quarantine policies implemented by the Iranian government was estimated to be insignificant concerning the mortality rate. However, the age range was an ifluential factor in mortality rate. Finally, the method proposed in the present study cofirmed the role of the mean age of the country in the mortality rate related to COVID-19 patients at the time of research conduction. The results indicated that if sever quarantine restrictions are not applied and Iranian government does not impose effective interventions, about 60% to 70% of the population (it means around 49 to 58 million people) would be afflicted by COVID-19 during June to September 2021.
. 2023 Mar 24;18(3):e0263991.
doi: 10.1371/journal.pone.0263991. eCollection 2023.
Neo-epidemiological machine learning based method for COVID-19 related estimations
Mouhamad Bodaghie[SUP] 1 [/SUP], Farnaz Mahan[SUP] 1 [/SUP], Leyla Sahebi[SUP] 2 [/SUP], Hossein Dalili[SUP] 3 [/SUP]
Affiliations
- PMID: 36961771
- DOI: 10.1371/journal.pone.0263991
Abstract
The 2019 newfound Coronavirus (COVID-19) still remains as a threatening disease of which new cases are being reported daily from all over the world. The present study aimed at estimating the related rates of morbidity, growth, and mortality for COVID-19 over a three-month period starting from Feb, 19, 2020 to May 18, 2020 in Iran. In addition, it revealed the effect of the mean age, changes in weather temperature and country's executive policies including social distancing, restrictions on travel, closing public places, shops and educational centers. We have developed a combined neural network to estimate basic reproduction number, growth, and mortality rates of COVID-19. Required data was obtained from daily reports of World Health Organization (WHO), Iran Meteorological Organization (IRIMO) and the Statistics Center of Iran. The technique used in the study encompassed the use of Artificial Neural Network (ANN) combined with Swarm Optimization (PSO) and Bus Transportation Algorithms (BTA). The results of the present study showed that the related mortality rate of COVID-19 is in the range of [0.1], and the point 0.275 as the mortality rate provided the best results in terms of the total training and test squared errors of the network. Furthermore, the value of basic reproduction number for ANN-BTA and ANN-PSO was 1.045 and 1.065, respectively. In the present study, regarding the closest number to the regression line (0.275), the number of patients was equal to 2566200 cases (with and without clinical symptoms) and the growth rate based on arithmetic means was estimated to be 1.0411 and 1.06911, respectively. Reviewing the growth and mortality rates over the course of 90 days, after 45 days of first case detection, the highest increase in mortality rate was reported 158 cases. Also, the highest growth rate was related to the eighth and the eighteenth days after the first case report (2.33). In the present study, the weather variant in relationship to the basic reproduction number and mortality rate was estimated ineffective. In addition, the role of quarantine policies implemented by the Iranian government was estimated to be insignificant concerning the mortality rate. However, the age range was an ifluential factor in mortality rate. Finally, the method proposed in the present study cofirmed the role of the mean age of the country in the mortality rate related to COVID-19 patients at the time of research conduction. The results indicated that if sever quarantine restrictions are not applied and Iranian government does not impose effective interventions, about 60% to 70% of the population (it means around 49 to 58 million people) would be afflicted by COVID-19 during June to September 2021.