AUTHOR=Wang Fei , Wang Pan , Wang Xihao , Lu Hengming , Han Yuchun , Wang Lianqu , Li Zhihui TITLE=Development and validation of a prediction model for the prognosis of renal cell carcinoma with liver metastases: a population-based cohort study JOURNAL=Frontiers in Medicine VOLUME=11 YEAR=2024 URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2024.1464589 DOI=10.3389/fmed.2024.1464589 ISSN=2296-858X ABSTRACT=Background

Current studies on the establishment of prognostic model for renal cell carcinoma (RCC) with liver metastases (LM) were scarce. This study aimed to develop nomograms to predict the prognosis of RCC with LM.

Methods

Patients diagnosed with RCC between 2010 and 2021 from the Surveillance, Epidemiology, and End Results (SEER) database were selected. The eXtreme Gradient Boosting (XGBoost) and Random Forest (RF) machine learning algorithms were used to screen for the most influential factors affecting prognosis, and the Venn diagram method was employed for further refinement. Subsequently, a nomogram related to brain metastases was constructed. The performance of the nomograms was evaluated through receiver operating characteristics (ROC) curves, calibration plots, C-index, time-dependent C-index, and decision curve analysis (DCA). Kaplan–Meier (K-M) survival curves were used to provide additional verification of the clinical efficacy of the nomogram.

Results

This research comprised 2,395 RCC patients with LM. The Venn diagram demonstrated that age, histological type, grade, AJCC T stage, AJCC N stage, surgery, chemotherapy, marital status, and lung metastasis were highly relevant variables to patients with LM. The AUC, C-index, calibration curves, and DCA curves showed excellent performance of the nomogram. Additionally, the prognostic nomogram accurately classified RCC with LM patients into low- and high-risk groups for mortality.

Conclusion

This study developed a novel nomogram to predict the prognostic factors of RCC with LM, providing a valuable reference for making accurate clinical decisions.