Development and validation of a multiphase CT radiomics-based machine learning model for prognostic prediction in sarcomatoid renal cell carcinoma
Abstract
BackgroundSarcomatoid renal cell carcinoma (sRCC) is a rare and aggressive subtype of renal cell carcinoma with a poor prognosis. Accurate prognostic stratification is critical for individualized treatment planning. This study aimed to develop and validate a machine learning-based prognostic model integrating multiphase CT radiomics and clinicopathological factors to predict overall survival (OS) in patients with pathology-confirmed sRCC.MethodsA total of 113 patients with pathologically confirmed sRCC who underwent nephrectomy were retrospectively enrolled. Radiomic features were extracted from arterial phase (AP) and venous phase (VP) CT images. After feature selection using intraclass correlation coefficient (ICC > 0.75) and univariate Cox regression, a radiomics signature was constructed using least absolute shrinkage and selection operator (Lasso) regression and random survival forest (RSF) algorithms. A combined model was developed by integrating the radiomics score with independent clinical predictors identified through multivariate Cox regression. Model performance was evaluated using the concordance index (C-index), time-dependent receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Internal validation was performed using bootstrap resampling and repeated cross-validation.ResultsThe combined model, incorporating the AP+VP radiomics score, N stage, M stage, and Ki-67 index, showed numerically improved predictive performance compared with the clinical model. In the held-out test set, it achieved a C-index of 0.737 (95% CI: 0.612–0.846), which was comparable to the AP+VP radiomics model alone (C-index: 0.735) and numerically higher than the clinical model (C-index: 0.615); however, the improvement over the clinical model was not statistically significant (P = 0.115). AUCs for 1-, 2-, and 3-year OS were 0.833, 0.780, and 0.749, respectively. The model showed good calibration and clinical utility across a range of threshold probabilities. Significant survival stratification was achieved between high- and low-risk groups (log-rank P < 0.05).ConclusionsThe proposed machine learning model combining multiphase CT radiomics and clinicopathological factors may provide a noninvasive tool for predicting OS in sRCC patients. It showed numerically improved performance compared with conventional clinical models; however, this incremental benefit was not statistically significant, and its performance was comparable to the radiomics-only model. Further multicenter validation is warranted to confirm its generalizability.
Related
- Development and validation of a prognostic prediction model for elderly patients with sepsis-associated acute kidney injury based on interpretable machine learning
- Development and validation of novel prognostic hepatic-cardiac index and hemodynamic prediction models in pre-capillary pulmonary hypertension patients
- A 2-year prognostic assessment of patients with coronary borderline lesions based on three-vessel quantitative flow ratio and the development and internal validation of a risk prediction nomogram
- Development and validation of a postoperative prognostic nomogram for early-stage pancreatic cancer
- Development and internal validation of a prognostic model for cancer-specific survival in elderly patients with metastatic non-small cell lung cancer: a SEER-based study
BibTeX
@article{liu2026development,
title = {{Development and validation of a multiphase CT radiomics-based machine learning model for prognostic prediction in sarcomatoid renal cell carcinoma}},
author = {Tongpeng Liu and Yu Yao and Zhijian Zhou and Yang Hu and Lijiang Sun and Guiming Zhang},
journal = {Frontiers in Oncology},
year = {2026},
month = oct,
doi = {10.3389/fonc.2026.1982796},
url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1982796},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Development and validation of a multiphase CT radiomics-based machine learning model for prognostic prediction in sarcomatoid renal cell carcinoma
AU - Tongpeng Liu
AU - Yu Yao
AU - Zhijian Zhou
AU - Yang Hu
AU - Lijiang Sun
AU - Guiming Zhang
PY - 2026
DA - 2026/10/30
JO - Frontiers in Oncology
DO - 10.3389/fonc.2026.1982796
UR - https://www.frontiersin.org/articles/10.3389/fonc.2026.1982796
AB - BackgroundSarcomatoid renal cell carcinoma (sRCC) is a rare and aggressive subtype of renal cell carcinoma with a poor prognosis. Accurate prognostic stratification is critical for individualized treatment planning. This study aimed to develop and validate a machine learning-based prognostic model integrating multiphase CT radiomics and clinicopathological factors to predict overall survival (OS) in patients with pathology-confirmed sRCC.MethodsA total of 113 patients with pathologically confirmed sRCC who underwent nephrectomy were retrospectively enrolled. Radiomic features were extracted from arterial phase (AP) and venous phase (VP) CT images. After feature selection using intraclass correlation coefficient (ICC > 0.75) and univariate Cox regression, a radiomics signature was constructed using least absolute shrinkage and selection operator (Lasso) regression and random survival forest (RSF) algorithms. A combined model was developed by integrating the radiomics score with independent clinical predictors identified through multivariate Cox regression. Model performance was evaluated using the concordance index (C-index), time-dependent receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Internal validation was performed using bootstrap resampling and repeated cross-validation.ResultsThe combined model, incorporating the AP+VP radiomics score, N stage, M stage, and Ki-67 index, showed numerically improved predictive performance compared with the clinical model. In the held-out test set, it achieved a C-index of 0.737 (95% CI: 0.612–0.846), which was comparable to the AP+VP radiomics model alone (C-index: 0.735) and numerically higher than the clinical model (C-index: 0.615); however, the improvement over the clinical model was not statistically significant (P = 0.115). AUCs for 1-, 2-, and 3-year OS were 0.833, 0.780, and 0.749, respectively. The model showed good calibration and clinical utility across a range of threshold probabilities. Significant survival stratification was achieved between high- and low-risk groups (log-rank P < 0.05).ConclusionsThe proposed machine learning model combining multiphase CT radiomics and clinicopathological factors may provide a noninvasive tool for predicting OS in sRCC patients. It showed numerically improved performance compared with conventional clinical models; however, this incremental benefit was not statistically significant, and its performance was comparable to the radiomics-only model. Further multicenter validation is warranted to confirm its generalizability.
SN - 2234-943X
ER -