key: cord-0061476-unb2fv2u
authors: Hariyanto, Timotius Ivan; Valeriani, Karunia; Kwenandar, Felix; Damay, Vika; Siregar, Jeremia Immanuel; Lugito, Nata Pratama Hardjo; Tjiang, Margaret Merlyn; Kurniawan, Andree
title: Deriving cut-off values through meta-analysis of individual studies
date: 2021-03-31
journal: Am J Emerg Med
DOI: 10.1016/j.ajem.2021.03.077
sha: 1c79fc11d5c1c3a12567b748db3a4d1241d86c8e
doc_id: 61476
cord_uid: unb2fv2u

nan

Dear Editor,

We have read with the great interest a letter to editor by Tandaju et al. [1] "Deriving cutoff values for continuous predictors of severe outcomes in COVID-19 through meta-analysis of individual studies: a comment on the article by Hariyanto et al." regarding one of our article titled "Inflammatory and hematologic markers as predictors of severe outcomes in COVID-19 infection: A systematic review and meta-analysis." [2] While it is not common to perform receiver operating characteristic (ROC) curves on meta-analysis study, however we think that it is still possible and also methodologically valid to perform ROC curves analysis based on study-level data. [3, 4] Several previously published meta-analysis have already done the same before us. They generated pooled ROC curve analysis based on sensitivity, specificity, and ROC curve of studylevel data. [5] [6] [7] Their studies were even cited by many other studies, meaning that another authors have acknowledged the results from their studies. We also agree that in meta-analysis, each studies will be given different weights according to the sample size and its variance in the fixedeffects or random-effects models, however if we look at the forest plot for each variables in our study, there is no study which have dominant weights and almost all included studies have similar weights from 5 -7%. Finally, we also agree that ROC curve analysis from study-level data could produce some bias, therefore the cut-off values from our study should be used with caution and as stated in our "Conclusion" section that further study is still needed regarding

Deriving cut-off values for continuous predictors of severe outcomes in COVID-19 through meta-analysis of individual studies: A comment on the article by Hariyanto et al

Inflammatory and hematologic markers as predictors of severe outcomes in COVID-19 infection: A systematic review and meta-analysis

Meta-analysis of ROC curves

Meta-analysis of diagnostic test accuracy assessment studies with varying number of thresholds

Diagnostic and prognostic value of hematological and immunological markers in COVID-19 infection: A meta-analysis of 6320 patients

Crucial laboratory parameters in COVID-19 diagnosis and prognosis: An updated meta-analysis. Med Clin (Barc)

IL-6 and IL-10 as predictors of disease severity in COVID-19 patients: results from meta-analysis and regression