EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

An explainable clinical–radiomics machine learning model for preoperative prediction of WHO/ISUP nuclear grade in clear cell renal cell carcinoma

Yue Li, Mingzhi Lin, Linlin Sun, Changming Dong, Jinshan Yang, Xinxin Li, Yuxin Lin, Jinting Wu, Junjie Zhao, Chunhua Lin

Abdominal Radiology · 2026

DOI: 10.1007/s00261-026-05521-1 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Abdominal Radiology, 2026. Verfasst von Yue Li und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, The Affiliated Yantai Yuhuangding Hospital of Qingdao University, Qingdao University, Qingdao, China. lyuedoctor@163.com. Hauptthemen laut MEDLINE: Radiomics, Carcinoma, Renal Cell, Kidney Neoplasms, Tomography, X-Ray Computed. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Natural Science Foundation of Shandong Province, China, the Yantai Science and Technology Innovation Development Plan, China, Taishan Scholar Program of Shandong Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Accurate preoperative assessment of the WHO/ISUP nuclear grade of clear cell renal cell carcinoma (ccRCC) is critical for guiding individualized surgical strategies and prognostic evaluation. However, current grading still depends on postoperative pathology. This study aimed to develop and validate a noninvasive, machine learning-based model integrating clinical and radiomic features for predicting WHO/ISUP pathological grade in ccRCC. METHODS: A total of 415 patients with pathologically confirmed ccRCC were retrospectively enrolled, including 320 for model development and 95 for external validation. Clinical variables significantly associated with tumor grade in univariate analysis were further analyzed using multivariate logistic regression and machine learning algorithms. Radiomic features were extracted from preoperative CT images and screened using three strategies: least absolute shrinkage and selection operator (LASSO), principal component analysis (PCA), and maximum relevance minimum redundancy (mRMR). Twelve algorithms-including Random Forest (RF), XGBoost, LightGBM, and Support Vector Machine (SVM)-were trained and validated. Model performance was evaluated by area under the curve (AUC), accuracy, sensitivity, specificity, and negative predictive value (NPV). Model interpretability was assessed using SHAP (SHapley Additive Explanations) analysis. RESULTS: Six independent predictors of WHO/ISUP grade were identified: body mass index (BMI), maximum tumor diameter, perirenal infiltration, serum albumin (SA), osmolality (OSM), and neuron-specific enolase (NSE). Among clinical-only models, RF achieved the best performance (AUC = 0.852, 0.734, and 0889 in training, test, and external validation cohorts, respectively). Incorporating radiomic features further improved prediction accuracy. In the combined LASSO-RF model, the external validation cohort achieved an AUC of 0.912 (95% CI: 0.854-0.970), accuracy of 0.853, sensitivity of 0917, and specificity of 0.831. SHAP analysis revealed that OSM, SA, and NSE were the most influential features, while radiomic texture features such as log-sigma-1-mm-3D first-order maximum also contributed significantly. CONCLUSION: The LASSO-RF model integrating clinical and radiomic features demonstrated excellent accuracy and generalizability for predicting WHO/ISUP grade in ccRCC. This noninvasive approach enables individualized preoperative grading and risk stratification, providing valuable support for nephron-sparing surgical decision-making and precision oncology in renal cancer management.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RadiomicsCarcinoma, Renal CellKidney NeoplasmsTomography, X-Ray ComputedMachine LearningHumansFemaleMaleRetrospective StudiesMiddle AgedNeoplasm GradingPredictive Learning ModelsAgedPredictive Value of TestsSensitivity and SpecificityAdultRandom Forest

Stichwörter der Autor:innen

Clear cell renal cell carcinoma (ccRCC)Machine learningRadiomicsRandom forestWHO/ISUP grading

Autor:innen und Institutionen

  • Department of Urology, The Affiliated Yantai Yuhuangding Hospital of Qingdao University, Qingdao University, Qingdao, China. lyuedoctor@163.com.
  • Lanzhou University Second Hospital, Lanzhou University, Lanzhou, China.
  • Department of Pulmonary and Critical Care Medicine, Yantaishan Hospital, Yantai, China.
  • Department of Urology, The Affiliated Yantai Yuhuangding Hospital of Qingdao University, Qingdao University, Qingdao, China.
  • Second Hospital of Shandong University, Weifang, China.
  • The Second Medical College, Binzhou Medical University, Yantai, China.

Förderung

  • Natural Science Foundation of Shandong Province, China
  • the Yantai Science and Technology Innovation Development Plan, China
  • Taishan Scholar Program of Shandong Province
  • Shandong Provincial Natural Science Foundation
  • The development of scientific and technological innovation in Yantai City

Zitieren

APA

Li, Y., Lin, M., Sun, L., Dong, C., Yang, J., Li, X., Lin, Y., Wu, J., Zhao, J., & Lin, C. (2026). An explainable clinical–radiomics machine learning model for preoperative prediction of WHO/ISUP nuclear grade in clear cell renal cell carcinoma. Abdominal Radiology. https://doi.org/10.1007/s00261-026-05521-1

Vancouver

Li Y, Lin M, Sun L, Dong C, Yang J, Li X, et al. An explainable clinical–radiomics machine learning model for preoperative prediction of WHO/ISUP nuclear grade in clear cell renal cell carcinoma. Abdominal Radiology. 2026. doi:10.1007/s00261-026-05521-1

BibTeX
@article{Li2026,
  author = {Li, Yue and Lin, Mingzhi and Sun, Linlin and Dong, Changming and Yang, Jinshan and Li, Xinxin and Lin, Yuxin and Wu, Jinting and Zhao, Junjie and Lin, Chunhua},
  title = {An explainable clinical–radiomics machine learning model for preoperative prediction of WHO/ISUP nuclear grade in clear cell renal cell carcinoma},
  journal = {Abdominal Radiology},
  year = {2026},
  doi = {10.1007/s00261-026-05521-1}
}
Kostenlos starten →