An individualized nomogram for survival prediction in intrahepatic cholangiocarcinoma: a population-based analysis

Intrahepatic cholangiocarcinoma (ICC) is an aggressive malignancy with poor prognosis. Current prognostic systems, including TNM staging system, incompletely incorporate important clinical and pathological factors. This study aims to develop and validate an individualized nomogram for predicting overall survival (OS) in ICC patients. A total of 1,751 ICC patients diagnosed between 2011 and 2021 were identified from the Surveillance, Epidemiology, and End Results (SEER) database for model development and internal validation. A temporally distinct SEER cohort of 751 ICC patients diagnosed between 2000 and 2010 was used for temporal validation. Twelve candidate predictors were prespecified, and the final nomogram variables were retained from the multivariable Cox model according to a predefined retention threshold. Model performance was evaluated using the concordance index (C-index), time-dependent area under the receiver operating characteristic curve (time-dependent AUC), calibration curves, decision curve analysis (DCA), and integrated discrimination improvement (IDI). Kaplan-Meier analysis was used for risk stratification. The nomogram demonstrated good discriminative ability, with C-indices of 0.761 (training cohort) and 0.732 (validation cohort), and time-dependent AUC values ranging from 0.74 to 0.84 across 1-, 3-, and 5-year predictions. Calibration curves revealed good agreement between predicted and observed survival probabilities in both cohorts. The model outperformed the TNM staging system, with IDI values of 0.197, 0.393, and 0.238 for 1-, 3-, and 5-year predictions, respectively (all P < 0.001). DCA indicated greater net benefit across a range of threshold probabilities. Risk stratification significantly differentiated high-risk from low-risk patients (log-rank P < 0.001). The proposed nomogram provides individualized prediction of 1-, 3-, and 5-year OS in ICC patients and may assist in risk stratification and prognostic assessment.