Estimating COVID-19 hospital demand using a non-parametric model: a case study in Galicia (Spain)
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
Understanding the demand for hospital beds for COVID-19 patients is key for decision-making and planning mitigation strategies, as overwhelming healthcare systems has critical consequences for disease mortality. However, accurately mapping the time-to-event of hospital outcomes, such as the length-of-stay in the ICU, requires understanding patient trajectories while adjusting for covariates and observation bias, such as incomplete data. Standard methods, like the Kaplan-Meier estimator, require prior assumptions that are untenable given current knowledge. Using real-time surveillance data from the first weeks of the COVID-19 epidemic in Galicia (Spain), we aimed to model the time-to-event and event probabilities of patients hospitalized, without parametric priors and adjusting for individual covariates. We applied a nonparametric Mixture Cure Model and compared its performance in estimating hospital ward/ICU lengths-of-stay to the performances of commonly used methods to estimate survival. We showed that the proposed model outperformed standard approaches, providing more accurate ICU and hospital ward length-of-stay estimates. Finally, we applied our model estimates to simulate COVID-19 hospital demand using a Monte Carlo algorithm. We provided evidence that adjusting for sex, generally overlooked in prediction models, together with age is key for accurately forecasting ICU occupancy, as well as discharge or death outcomes.
Article activity feed
-
SciScore for 10.1101/2020.09.04.20187963: (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
No key resources detected.
Results from OddPub: Thank you for sharing your code.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Last, we would like to highlight key limitations of our model: the lack of a parametric function limits interpretability to a great extent and complicates handling several covariates simultaneously [31]. Regarding the application of MCM, there must be good evidence that some individuals in the population will never experience the event of interest and the follow-up time must be long enough [32]. Furthermore, there is no method in the literature …
SciScore for 10.1101/2020.09.04.20187963: (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
No key resources detected.
Results from OddPub: Thank you for sharing your code.
Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:Last, we would like to highlight key limitations of our model: the lack of a parametric function limits interpretability to a great extent and complicates handling several covariates simultaneously [31]. Regarding the application of MCM, there must be good evidence that some individuals in the population will never experience the event of interest and the follow-up time must be long enough [32]. Furthermore, there is no method in the literature to construct confidence intervals or confidence bands for the NP-MCM estimator. Finally, data on patient comorbidities, which likely represents an important source of heterogeneity in the LoS, were not available for the analysis. Thus, more accurate estimates of the different LoS can be obtained if more complete datasets are available. In summary, we implemented a NP-MCM that improved the standard survival methodology when estimating LoS until final outcomes that will not happen for all patients. We also found that the LoS in the ICU is sensitive to age and sex, which in turn is relevant when forecasting hospital demand in real-time for public health response. We believe our proposed approach can be easily implemented in other settings and can provide more accurate estimates of COVID-19 health demand compared to previous methods.
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.
-
-
-