Volume 9, Issue 1 (6-2022)
jhbmi 2022, 9(1): 27-39 |
Back to browse issues page
Download citation:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
BibTeX | RIS | EndNote | Medlars | ProCite | Reference Manager | RefWorks
Send citation to:
Makhloughi F, Goshvarpour A. Prediction of Covid-19 Prevalence and Fatality Rates in Iran Using Long Short-Term Memory Neural Network. jhbmi 2022; 9 (1) :27-39
URL: http://jhbmi.ir/article-1-667-en.html
URL: http://jhbmi.ir/article-1-667-en.html
PhD Biomedical Engineering, Assistant Professor of Biomedical Engineering, Department of Biomedical Engineering, Imam Reza International University, Mashhad, Razavi Khorasan, Iran
Abstract: (1489 Views)
Introduction: The rapid spread of COVID-19 has become a critical threat to the world. So far, millions of people worldwide have been infected with the disease. The Covid-19 pandemic has had significant effects on various aspects of human life. Currently, prediction of the virus's spread is essential in order to be safe and make necessary arrangements. It can help control the rate of its outbreak and deaths. Previous studies have mainly used statistical tools and machine learning-based algorithms. However, the former was inadequate for analyzing unpredictable epidemics, and the latter experienced under-fitting or over-fitting problems. This research has proposed a method based on deep learning on long-term data to overcome these problems.
Method: In this cross-sectional analytical study, we presented an approach for predicting the confirmed and death cases of COVID-19 based on long short-term memory (LSTM) networks. The LSTM model was applied to the time series data of Iran between January 22, 2020, and December 14, 2021, and RMSE and MAE evaluation metrics were calculated.
Results: The best results of this study were RMSE = 27.57 and MAE = 19.01 for predicting death cases data. The results showed that the LSTM neural network had a good performance in predicting the number of confirmed and death cases of COVID-19 in Iran.
Conclusion: The proposed model showed that it was appropriate for modeling and predicting the prevalence of the virus. Estimating the number of confirmed and death cases of COVID-19 can help control the pandemic situation.
Method: In this cross-sectional analytical study, we presented an approach for predicting the confirmed and death cases of COVID-19 based on long short-term memory (LSTM) networks. The LSTM model was applied to the time series data of Iran between January 22, 2020, and December 14, 2021, and RMSE and MAE evaluation metrics were calculated.
Results: The best results of this study were RMSE = 27.57 and MAE = 19.01 for predicting death cases data. The results showed that the LSTM neural network had a good performance in predicting the number of confirmed and death cases of COVID-19 in Iran.
Conclusion: The proposed model showed that it was appropriate for modeling and predicting the prevalence of the virus. Estimating the number of confirmed and death cases of COVID-19 can help control the pandemic situation.
Type of Study: Original Article |
Subject:
Artificial Intelligence in Healthcare
Received: 2022/01/3 | Accepted: 2022/06/25
Received: 2022/01/3 | Accepted: 2022/06/25
Audio File [M4A 3169 KB] (33 Download)
Send email to the article author
| Rights and permissions | |
 |
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License. |
