Table 10 shows the comparative results of the DT and LR models constructed from four sets of prognosis variables: the nine prognosis variables (in Table 3), the variables previously used by Delen et al. [ 8], the variables previously used by Endo et al. [ 10], and all selected predictor variables (Additional file 1: Table S2).
The result of Tukey's HSD test in Table 12 shows that the performance of C_LR_9 constructed by using the nine prognosis variables is indifferent from U_LR_20 model constructed by using more variables (20 variables).
In the multivariate analysis, several characteristics were identified as independent poor prognosis variables: poor performance status, weight loss equal to or greater than 5%, stage equal to or greater than IIIb and SCS greater than 9.
We aimed in this study to evaluate the expression of EMMPRIN in patients with OSCC and investigate the association of this glycoprotein with clinicopathological, tumor proliferation, and prognosis variables.
To show that SMOTE, CSC, under-sampling, bagging and AdaboostM1 can improve the predictive performance of the original models, we input nine prognosis variables (see Table 3) for S_DT_9, S_LR_9, C_DT_9, C_LR_9, U_DT_9, U_LR_9, Ba_DT_9, Ba_LR_9, Ad_DT_9, and Ad_LR_9 model constructions.
Although the technology used has been shown to be ready for clinical practice [ 16], and can be used as one parameter in combination with current clinical parameters, these signatures need to be prospectively validated to prove their superiority and benefit above and beyond the use of standard clinico-pathological prognosis variables to guide the choice of adjuvant therapy.
Using an expression data set of 649 NBs with associated prognostic information, the poor prognosis variables of age >18 months at diagnosis, stage 4 disease and MYCN amplification were all highly associated with high expression of SART1, UBL5, PRPF8 and SF3B1 at P<0.001, except for PRPF8 and MYCN amplification (P=0.11; Supplementary Figure S5).
This diagnosis is made solely through histology, and its prognosis is variable [2, 5].
The prognosis is variable and mortality ranges from 8to50%0%.
For accurate prediction of RCC prognosis, one variable alone is not sufficient.
