Application of latent class analysis in diagnosis of graft-versus-host disease by serum markers after allogeneic haematopoietic stem cell transplantation

Abstract

2 for a composite test is as the same as a diagnostic test. For choosing optimal cutoff point, the Youden index which mentioned before, was used for the combinations. Afterward, the cSensitivity and cSpecificity were selected. For the models, the convergence of the MCMC chains for all the LCMs (with and without covariate adjustment) was assessed using autocorrelation plots. Furthermore, the convergence was obtained by running one chain with 35,000 iterations with lag 45. The first 17,000 iterations were discarded. The Bayesian latent class models were fitted by using OpenBUGS 3.2.1 41. The R package R2OpenBUGS 42 also applied as an interface between R 3.6.2 43 and OpenBUGS. After determining the GVHD groups based on optimal composite test, in order to evaluate the association between each of continuous variables and GVHD, an independent sample t-test was performed and chi-square test was applied for each categorical variable. All comparisons were two-tailed and p-value of less than 0.05 was taken as statistically significant. Descriptive analyses were performed using R version 3.6.2.

An Intelligent Clinical Decision Support System for Predicting Acute Graft-versus-host Disease (aGvHD) following Allogeneic Hematopoietic Stem Cell Transplantation

“…Studies have shown that low levels of LDH and high levels of serum cyclosporine reduce the likelihood of aGvHD [ 51 ]. In some previous studies, this variable has been presented as one of the important predictors [ 10 , 52 ].…”