A semi-parametric, state-space compartmental model with time-dependent parameters for forecasting COVID-19 cases, hospitalizations and deaths
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
Short-term forecasts of the dynamics of coronavirus disease 2019 (COVID-19) in the period up to its decline following mass vaccination was a task that received much attention but proved difficult to do with high accuracy. However, the availability of standardized forecasts and versioned datasets from this period allows for continued work in this area. Here, we introduce the Gaussian infection state space with time dependence (GISST) forecasting model. We evaluate its performance in one to four weeks ahead forecasts of COVID-19 cases, hospital admissions and deaths in the state of California made with official reports of COVID-19, Google’s mobility reports and vaccination data available each week. Evaluation of these forecasts with a weighted interval score shows them to consistently outperform a naive baseline forecast and often score closer to or better than a high-performing ensemble forecaster. The GISST model also provides parameter estimates for a compartmental model of COVID-19 dynamics, includes a regression submodel for the transmission rate and allows for parameters to vary over time according to a random walk. GISST provides a novel, balanced combination of computational efficiency, model interpretability and applicability to large multivariate datasets that may prove useful in improving the accuracy of infectious disease forecasts.
Article activity feed
-
-
-
SciScore for 10.1101/2021.09.02.21262995: (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
Experimental Models: Organisms/Strains Sentences Resources The initial value of ⟨ X ⟩ is set to N − ⟨ L ⟩ − ⟨ Y ⟩ − ⟨ H ⟩ − ⟨ D ⟩. N − ⟨ L ⟩ − ⟨ Y ⟩ − ⟨ H ⟩ −suggested: NoneSoftware and Algorithms Sentences Resources An archive of the code used to obtain the data and generate all results is available on Zenodo at https://doi.org/10.5281/zenodo.5112578. Zenodosuggested: (ZENODO, RRID:SCR_004129)Results from OddPub: Thank you for sharing your data.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Another limitation of the GISST model, as we have presented it here, may be that it …
SciScore for 10.1101/2021.09.02.21262995: (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
Experimental Models: Organisms/Strains Sentences Resources The initial value of ⟨ X ⟩ is set to N − ⟨ L ⟩ − ⟨ Y ⟩ − ⟨ H ⟩ − ⟨ D ⟩. N − ⟨ L ⟩ − ⟨ Y ⟩ − ⟨ H ⟩ −suggested: NoneSoftware and Algorithms Sentences Resources An archive of the code used to obtain the data and generate all results is available on Zenodo at https://doi.org/10.5281/zenodo.5112578. Zenodosuggested: (ZENODO, RRID:SCR_004129)Results from OddPub: Thank you for sharing your data.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Another limitation of the GISST model, as we have presented it here, may be that it is missing important covariates in the regression model for the transmission rate (Eq 4). For example, we have not tried using other mobility metrics provided in the Google Community mobility reports. On the one hand, predicting future values of such covariates could be just as challenging as predicting future values of COVID-19 indicators without them. One might address this problem to some extent by applying a penalty proportional to the absolute value of the regression coefficient of these covariates, which would shrink the effect of unimportant covariates to zero. This approach would be readily achievable with the optimizer we used by choosing the Orthant-Wise Limited-memory Quasi-Newton (OWL-QN) algorithm instead of the LBFGS algorithm. The use of this option is what we alluded to in the introduction as the ability of GISST to search for important variables from a large space of candidate variables. Variables identified in this manner may sufficiently lead the indicators we wish to forecast that they improve forecasts just by being available up to or close to the date of forecast. Knowing which variables are important for predicting the transmission rate, even if they are difficult to forecast, could also be valuable for the design of forecasts.
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.
Results from scite Reference Check: We found no unreliable references.
-