Development of a radiomic model to predict CEACAM1 expression and prognosis in ovarian cancer

Abstract

We aimed to investigate the prognostic role of CEACAM1 and to construct a radiomic model to predict CEACAM1 expression and prognosis in ovary cancer (OC). Sequencing data and CT scans in OC were sourced from TCGA and TCIA databases. CEACAM1 expression was assessed by Cox regression analyses, Kaplan-Meier curves and GSVA enrichment analysis. Furthermore, radiomic features were extracted from CT scans and selected by LASSO and ROC. The selected radiomic features were used to construct a radiomic model to predict CEACAM1 expression. In addition, the radiomic score (RS) and its relationship with OC survival were investigated by Kaplan-Meier and ROC curves. At last, RS and clinical features were included into LASSO, using nomogram to predict OC prognosis. Cox regression analyses showed that CEACAM1 expression was an independent prognostic factor and associated with immune cell infiltration in OC. By LASSO and ROC, six radiomic features were selected and used to construct a radiomic model. The PR, calibration, DCA and ROC curves revealed the good performance and clinical utility of the radiomic model to predict CEACAM1 expression. In addition, RS based on radiomic features was found to be associated with OC survival. At last, a nomogram based on RS, age, chemotherapy and tumor residual disease was constructed and was found to have high accuracy in predicting OC prognosis. For the first time, our study constructed a radiomic model to predict CEACAM1 expression and prognosis of OC patients. Those findings may guide novel diagnosis and treatment for OC patients.

Keywords: CEACAM1; Ovarian cancer; Prognosis; Radiomics.

Fig. 1

CEACAM1 expression is an independent prognostic factor in ovary cancer. (A) The expressions of CEACAM1 between tumor and control samples. (B) Uni- and multiple Cox analyses on the CEACAM1 expression and co-variates. (C) Univariate subgroup analysis and interaction test.

Fig. 2

CEACAM1high and CEACAM1low expression groups have different characteristics. (A) Kaplan-Meier curves showing the survival of two groups. (B) Comparison of immune infiltration between two groups. (C) GSVA analysis of two groups using hallmarks as reference gene sets. (D) GSVA analysis of two groups using KEGG pathways as reference gene sets.

Fig. 3

Radiomic feature selection by LASSO. (A) Selection of the tuning parameter (Lambda) in the LASSO model. The optimal lambda value with log (λ) = -2.349 was selected. (B) LASSO coefficient profiles of extracted radiomic features. (C) Histogram showing the importance of six selected radiomic features.

Fig. 4

Assessment of the logistic model in predicting CEACAM1 expression. (A) PR curve. (B) Calibration curve. (C) DCA curves. (D) ROC curve in the training set. (E) ROC curve in the validation set.

Fig. 5

Radiomic score (RS) is associated with OC survival. (A) Kaplan-Meier curves showing the survival of RShigh and RSlow group. (B) ROC curves of RS to predict 1-, 3- and 5-year survival of OC. (C) Selection of the tuning parameter (Lambda) in the LASSO model. (D) LASSO coefficient profiles of RS and clinical features.

Fig. 6

A nogmogram is constructed to predict OC prognosis. (A) The nomogram for the prediction of 1-, 3- and 5-year survival of OC patients. (B) Calibration curves. (C) ROC curves.