Abstract
To develop a nomogram model which combined clinical inflammatory indicators and CT radiomics features to predict progression free survival (PFS) in esophageal squamous cell carcinoma (ESCC) after radical operation. 258 ESCC patients receiving surgical operation treatment were retrospectively collected from July 2017 to March 2019. Clinical data, laboratory results, pathology results, pre-operative CT data, and survival outcomes were analyzed. Using cox proportional hazards regression model to assess the relationship between relevant clinicopathological factors and PFS. C-index and calibration curve were used to evaluate the nomogram model. Survival curves were obtained using the Kaplan-Meier and comparisons were made by using the log-rank test. The inflammatory model, radiomics model and nomogram model all have good predictive efficacy for predicting PFS of ESCC patients in both training and test set. Significant differences were found between the nomogram model and inflammatory model and the radiomics model (DeLong test, Z = 3.869 and 3.195, P < 0.001, P = 0.001). Decision curve analysis (DCA) results revealed the net benefit of nomogram model was better than that of inflammatory model and radiomics model. Kaplan-Meier results showed significant difference in PFS between high-risk and low-risk group in Radscore and nomogram model (P < 0.001), and the high-risk group was prone to postoperative recurrence and poor PFS. The nomogram model developed by combining inflammatory indicators and radiomics features, which is helpful for risk stratification and follow-up work, and improving ESCC patients' prognosis.