Cumulative risk of all-cause death was displayed using corresponding Kaplan-Meier plots. To examine the relationship between all-cause death and cTn measurements, we used the Cox proportional hazard model. Continuous variables including log (x ULN), age, NLR, D-Dimer, LDH, CRP, hemoglobin, platelet count were included in the model as flexible smooth parameters using a restricted cubic spline.

We fitted different models according to the cTn measurement included in the model [cTn xULN were included as a continuous variable with and without spline function in model-1, ordinal variable in model-2, and dichotomic (positive/negative) variable in the model-3]. We also included the interaction term for cTn*age, cTn*HF, and cTn*CKD to test for the statistical significance of effect modification by age, HF, and CKD. We also tested the interaction between number of comorbities and cTn in a separate model. The associations between candidate predictors and all-cause death were quantified by the adjusted hazard ratio with a 95% confidence interval (CI). The hazard ratios (HR) for continuous variables with splines represents an increase from the 25th to the 75th percentile. We retained all candidate predictors in the model and did not remove any of these predictors based on statistical significance. The relative importance of each predictor in the models was estimated with partial X [2] value for each predictor divided by the model's total X [2], which estimated the independent contribution of each predictor to the variance of the outcome. The variables having missing value > 20% were not included in the model (except for D-Dimer and LDH, their missingness were about 40%), while for that < 20%, with the assumption of missing at random, multiple imputations were used either to minimize bias and to avoid exclusions of participants. Multiple imputations were applied for missing values using aregImpute function (rms). Five completed datasets were analyzed, and results were combined by Rubin's rule [22]. For all statistical analyses, we used R-software v. 3.5.1 (R statistical software, Institute for statistics and mathematics, Vienna, Austria).

Note: The content above has been extracted from a research article, so it may not display correctly.



Q&A
Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.



We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.