Skip to main content
Fig. 5 | Cancer Cell International

Fig. 5

From: Robust machine−learning based prognostic index using cytotoxic T lymphocyte evasion genes highlights potential therapeutic targets in colorectal cancer

Fig. 5

CERPI for clinical applications. The high−CERPI patients were more likely to have advanced−stage CRC in TCGA−CRC (n = 506) (A), GSE39582 (n = 573) (B), and GSE17536 (n = 177) (C) datasets; however, this trend was not significant in the GSE72970 (n = 124) dataset (D). TCGA−CRC and GSE39582 datasets were used to perform univariate (E) and multivariate (F) Cox regression analyses. Clinical features that exhibited significant associations with patient prognosis in both univariate and multivariate analyses were utilized in the construction of the nomogram model. Calibration plots demonstrated a high level of prediction accuracy for the nomograms in the TCGA−CRC dataset (G) and the GSE39582 dataset (H)

Back to article page

Cancer Cell International

ISSN: 1475-2867

Contact us