Forecasting American COVID-19 Cases and Deaths through Machine Learning
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
COVID-19 has become a great national security problem for the United States and many other countries, where public policy and healthcare decisions are based on the several models for the prediction of the future deaths and cases of COVID-19. While the most commonly used models for COVID-19 include epidemiological models and Gaussian curve-fitting models, recent literature has indicated that these models could be improved by incorporating machine learning. However, within this research on potential machine learning models for COVID-19 forecasting, there has been a large emphasis on providing an array of different types of machine learning models rather than optimizing a single one. In this research, we suggest and optimize a linear machine learning model with a gradient-based optimizer for the prediction of future COVID-19 cases and deaths in the United States. We also suggest that a hybrid of a machine learning model for shorter range predictions and a Gaussian curve-fitting model or an epidemiological model for longer range predictions could greatly increase the accuracy of COVID-19 forecasting.
Article activity feed
-
SciScore for 10.1101/2020.08.13.20174631: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources To create these models, we downloaded and pre-processed the data from the New York Times’ github using several common Python libraries to create the input and output arrays described above. Pythonsuggested: (IPython, RRID:SCR_001658)Results from OddPub: Thank you for sharing your code and data.
Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.Results from TrialIdentifier: No clinical trial numbers were referenced.
Results from Barzooka: We did not find any …
SciScore for 10.1101/2020.08.13.20174631: (What is this?)
Please note, not all rigor criteria are appropriate for all manuscripts.
Table 1: Rigor
NIH rigor criteria are not applicable to paper type.Table 2: Resources
Software and Algorithms Sentences Resources To create these models, we downloaded and pre-processed the data from the New York Times’ github using several common Python libraries to create the input and output arrays described above. Pythonsuggested: (IPython, RRID:SCR_001658)Results from OddPub: Thank you for sharing your code and data.
Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.Results from TrialIdentifier: No clinical trial numbers were referenced.
Results from Barzooka: We did not find any issues relating to the usage of bar graphs.
Results from JetFighter: We did not find any issues relating to colormaps.
Results from rtransparent:- Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
- Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
- No protocol registration statement was detected.
-
-