Probabilistic analysis of COVID-19 patients’ individual length of stay in Swiss intensive care units
This article has been Reviewed by the following groups
Listed in
- Evaluated articles (ScreenIT)
Abstract
The COVID-19 pandemic induces considerable strain on intensive care unit resources.
Objectives
We aim to provide early predictions of individual patients’ intensive care unit length of stay, which might improve resource allocation and patient care during the on-going pandemic.
Methods
We developed a new semiparametric distributional index model depending on covariates which are available within 24h after intensive care unit admission. The model was trained on a large cohort of acute respiratory distress syndrome patients out of the Minimal Dataset of the Swiss Society of Intensive Care Medicine. Then, we predict individual length of stay of patients in the RISC-19-ICU registry.
Measurements
The RISC-19-ICU Investigators for Switzerland collected data of 557 critically ill patients with COVID-19.
Main results
The model gives probabilistically and marginally calibrated predictions which are more informative than the empirical length of stay distribution of the training data. However, marginal calibration was worse after approximately 20 days in the whole cohort and in different subgroups. Long staying COVID-19 patients have shorter length of stay than regular acute respiratory distress syndrome patients. We found differences in LoS with respect to age categories and gender but not in regions of Switzerland with different stress of intensive care unit resources.
Conclusion
A new probabilistic model permits calibrated and informative probabilistic prediction of LoS of individual patients with COVID-19. Long staying patients could be discovered early. The model may be the basis to simulate stochastic models for bed occupation in intensive care units under different casemix scenarios.
Article activity feed
-
-
SciScore for 10.1101/2020.09.29.20203612: (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:Second, a limitation is imposed by the use of MDSi as training dataset because the analysis is then constrained to the relatively few variables contained in MDSi. However, since some of these are compound variables, they are informative for the LoS. Furthermore, if training data sets with more covariates are available, the model can readily be adapted and predictive skill may increase. Second, there is possibly a bias towards a longer predicted …
SciScore for 10.1101/2020.09.29.20203612: (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:Second, a limitation is imposed by the use of MDSi as training dataset because the analysis is then constrained to the relatively few variables contained in MDSi. However, since some of these are compound variables, they are informative for the LoS. Furthermore, if training data sets with more covariates are available, the model can readily be adapted and predictive skill may increase. Second, there is possibly a bias towards a longer predicted LoS because of the data sampling process. We have assessed whether the patients with missing LoS value in the RISC-19-ICU registry have a substantially different distribution of covariate values than the patients with valid LoS value. This is not the case which is an indication that many of them, rather than having a censored LoS, have indeed not been updated. We have also repeated all of our analyses on the COVID-19 dataset restricted to patients with admission date before April 5, 2020. Here, the update and the censoring problem should be less. Qualitatively, we obtained the same results as the ones reported here. Nevertheless, it should be kept in mind that some of the very long LoS are likely to be censored in either case. Third, LoS is often not only dependent on epidemiologic and physiologic variables but additionally on ICU resources, therapeutic restriction policies [20] and withdrawal strategies (https://www.samw.ch/de/Ethik/Themen-A-bis-Z/Intensivmedizin.html). Our forecasts predict a longer LoS compared with the observed LOS...
Results from TrialIdentifier: We found the following clinical trial numbers in your paper:
Identifier Status Title NCT04357275 Recruiting The RIsk Stratification in COVID-19 Patients in the ICU Regi… 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.
-
