Current best evidence for clinical care (more info)
Background: To develop a sensitive risk score predicting the risk of mortality in patients with coronavirus disease 2019 (COVID-19) using complete blood count (CBC).
Methods: We performed a retrospective cohort study from a total of 13,138 inpatients with COVID-19 in Hubei, China, and Milan, Italy. Among them, 9,810 patients with =2 CBC records from Hubei were assigned to the training cohort. CBC parameters were analyzed as potential predictors for all-cause mortality and were selected by the generalized linear mixed model (GLMM).
Findings: Five risk factors were derived to construct a composite score (PAWNN score) using the Cox regression model, including platelet counts, age, white blood cell counts, neutrophil counts, and neutrophil:lymphocyte ratio. The PAWNN score showed good accuracy for predicting mortality in 10-fold cross-validation (AUROCs 0.92-0.93) and subsets with different quartile intervals of follow-up and preexisting diseases. The performance of the score was further validated in 2,949 patients with only 1 CBC record from the Hubei cohort (AUROC 0.97) and 227 patients from the Italian cohort (AUROC 0.80). The latent Markov model (LMM) demonstrated that the PAWNN score has good prediction power for transition probabilities between different latent conditions.
Conclusions: The PAWNN score is a simple and accurate risk assessment tool that can predict the mortality for COVID-19 patients during their entire hospitalization. This tool can assist clinicians in prioritizing medical treatment of COVID-19 patients.
Funding: This work was supported by National Key R&D Program of China (2016YFF0101504, 2016YFF0101505, 2020YFC2004702, 2020YFC0845500), the Key R&D Program of Guangdong Province (2020B1111330003), and the medical flight plan of Wuhan University (TFJH2018006).
|Discipline / Specialty Area||Score|
Another prognostic prediction model for hospitalized patients with COVID-19. Practical application limited to situations where constrained resources dictate treatment allocation.
The authors present a model for predicting mortality based on CBC trajectories with an extraordinarily high performance and appropriate methodology; however, the score is going to be complicated to use for the bedside provider. The main takeaways - that NLR is a predictor of outcomes and that platelet drops portend poor outcomes - are qualitatively known, but this paper does a reasonable job of demonstrating the quantitative impact of these combined effects.
Nice simple predictor of mortality in COVID patients using only age and data from CBC and validated in other cohorts. In developed countries, other possibly useful information is usually also available, so other risk scores might be even more useful.
This is a novel and interesting study of a mortality risk calculator for COVID patients using only the complete blood count. The authors use 5 components for the model that has an impressive predictability. It is not clear, however, whether there is need for this or whether it is superior to the SOFA score. Despite the authors validating this prediction model with an independent cohort, it may benefit from another independent validation.