Development of web-based dynamic nomogram to predict survival in patients with gastric cancer: a population-based study

Abstract

Gastric cancer (GC) is the fifth most frequent malignancy worldwide and the third leading cause of cancer-associated mortality. The study's goal was to construct a predictive model and nomograms to predict the survival of GC patients. This historical cohort study assessed 733 patients who underwent treatments for GC. The univariate and multivariable Cox proportional hazard (CPH) survival analyses were applied to identify the factors related to overall survival (OS). A dynamic nomogram was developed as a graphical representation of the CPH regression model. The internal validation of the nomogram was evaluated by Harrell's concordance index (C-index) and time-dependent AUC. The results of the multivariable Cox model revealed that the age of patients, body mass index (BMI), grade of tumor, and depth of tumor elevate the mortality hazard of gastric cancer patients (P < 0.05). The built nomogram had a discriminatory performance, with a C-index of 0.64 (CI 0.61, 0.67). We constructed and validated an original predictive nomogram for OS in patients with GC. Furthermore, nomograms may help predict the individual risk of OS in patients treated for GC.

Figure 1

Kaplan–Meier survival curves by American joint committee on cancer staging, along with the number at risks in gastric cancer patients.

Figure 2

Predictive nomogram for survival in Gastric cancer patients.

Figure 3

Web-based survival rate calculator (Dynamic Nomogram (shinyapps.io)) to predict the survival of GC patients; Two patients who are 77 years old, no surgery, no family history, PT3 and 25 ≤ BMI < 30, but have different grade, well (black line) and poorly (blue line), according to the web survival rate calculator.

Figure 4

(A) Time-dependent AUC summary at evaluation time points. (B) Decision curve analysis. (C) Internal calibration using bootstrap resampling at 1 year and 2 years.