Abstract
BACKGROUND: Chemotherapy is an important treatment for intrahepatic cholangiocarcinoma (ICC) patients, but there is a lack of survival prediction models. This study aims to develop a nomogram to predict cancer-specific survival (CSS) in ICC patients receiving chemotherapy. METHODS: A retrospective analysis was performed using data from the Surveillance, Epidemiology, and End Results (SEER) database involving 1,363 ICC patients who receiving chemotherapy between 2010 and 2019. The patients were randomly allocated in a 7:3 ratio to the training cohort and validation cohort. Cox proportional hazards regression analysis was employed to identify prognostic factors for nomogram construction. The accuracy of the model was assessed using the concordance index (C-index), area under the curve (AUC) value, and calibration curve. Additionally, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI) were utilized to evaluate the clinical value of the nomogram and to compare it with tumor staging based on American Joint Committee on Cancer (AJCC) criteria. RESULTS: Multivariate Cox regression analysis selected seven variables to establish the nomogram. The C-index and AUC value indicate that the nomogram has high accuracy. The calibration curve shows good consistency between the actual observed values and the nomogram-predicted CSS. Meanwhile, DCA, NRI, and IDI demonstrate that the nomogram has significant clinical applicability compared to tumor staging based on AJCC criteria. Furthermore, a risk classification system with satisfactory ability to identify different-risk patients was established. CONCLUSIONS: We have developed a nomogram for predicting the prognosis of ICC patients receiving chemotherapy, which can effectively assess the prognosis of this patient population.