Exploratory clinical-CT machine learning characterization of CK7 expression in clear cell renal cell carcinoma
5 affiliations
- 1Department of Radiology, Quanzhou First Hospital Affiliated to Fujian Medical University
- 2Department of Radiology, Zhongshan Hospital, Fudan University
- 3Department of Pathology, Zhongshan Hospital, Fudan University
- 4Department of Radiology, Ninghai First Hospital
- 5Department of Radiology, Xiamen Branch, Zhongshan Hospital, Fudan University
Abstract
Background Cytokeratin 7 (CK7) expression in clear cell renal cell carcinoma (ccRCC) may reflect tumor phenotype and biological heterogeneity, but its clinical role remains exploratory. This study aimed to investigate associations between preoperatively available clinical and CT imaging features and CK7 expression and to develop an exploratory machine learning model for CK7 characterization. Methods This multicenter retrospective study included 230 patients with pathologically confirmed ccRCC from three institutions, including 139 patients in the training cohort and 91 patients in the validation cohort. Clinical variables and qualitative and quantitative CT features were assessed by two radiologists. CK7 positivity was defined as cytoplasmic staining in at least 10% of tumor cells. After least absolute shrinkage and selection operator regression, four machine learning models using prespecified configurations were developed in the training cohort and evaluated in the validation cohort. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, accuracy, F1 score, calibration analysis, and decision curve analysis. Classification thresholds were determined in the training cohort using the maximum Youden index and then applied to the validation cohort. Model stability was assessed using 1000 bootstrap resampling iterations. Results Among 230 patients, 67 had CK7-positive tumors. The final predictors included age, cystic component, corticomedullary attenuation, corticomedullary enhancement ratio, nephrographic attenuation, and tumor size. The logistic regression model was selected as the final model based on its discrimination, calibration performance, interpretability, and overall generalizability. In the validation cohort, the logistic regression model achieved an AUC of 0.714 (95% CI: 0.589, 0.828), with a sensitivity of 0.625 and a specificity of 0.627. Bootstrap resampling supported the stability of performance estimates. Conclusion This exploratory machine learning model-development study suggests that preoperatively available clinical and CT imaging features may be associated with CK7 expression in ccRCC. Further prospective validation using larger cohorts is required before clinical translation.
Related
- Folic Acid Oversupplementation Alters Global DNA Methylation and Circadian Clock Gene Expression in FaDu Head and Neck Squamous Cell Carcinoma Cells: An Exploratory Study
- A dual-branch CNN-LSTM framework for exploratory classification of colorectal cancer histopathology and hepatocellular carcinoma clinical records
- Baseline Host Biomarkers and Six-Month Sustained Drug-Free Status After Atezolizumab–Bevacizumab for Hepatocellular Carcinoma: Exploratory Clinical Stratification Using PAN-DF Score
- TFAP2E Expression Is Associated with Survival and a Transcriptomic Pattern in Ovarian Serous Carcinoma, Supported by Hallmark and Protein-Level Characterization
- Urinary Incontinence Among Community-Dwelling Older Women: An Exploratory Cross-Sectional Characterization of Clinical Features, Urinary Habits, and Perceptions
BibTeX
@article{lin2026exploratory,
title = {{Exploratory clinical-CT machine learning characterization of CK7 expression in clear cell renal cell carcinoma}},
author = {Qiansen Lin and Gengyun Miao and Xi Jia and Yuxiu Zhang and Chunpeng Niu and Heqing Wang and Jieyun Chen and Liheng Liu},
journal = {BMC Cancer},
year = {2026},
month = jul,
doi = {10.1186/s12885-026-16567-1},
url = {https://doi.org/10.1186/s12885-026-16567-1},
note = {CC BY},
}
RIS
TY - JOUR
TI - Exploratory clinical-CT machine learning characterization of CK7 expression in clear cell renal cell carcinoma
AU - Qiansen Lin
AU - Gengyun Miao
AU - Xi Jia
AU - Yuxiu Zhang
AU - Chunpeng Niu
AU - Heqing Wang
AU - Jieyun Chen
AU - Liheng Liu
PY - 2026
DA - 2026/07/01
JO - BMC Cancer
DO - 10.1186/s12885-026-16567-1
UR - https://doi.org/10.1186/s12885-026-16567-1
AB - Background Cytokeratin 7 (CK7) expression in clear cell renal cell carcinoma (ccRCC) may reflect tumor phenotype and biological heterogeneity, but its clinical role remains exploratory. This study aimed to investigate associations between preoperatively available clinical and CT imaging features and CK7 expression and to develop an exploratory machine learning model for CK7 characterization. Methods This multicenter retrospective study included 230 patients with pathologically confirmed ccRCC from three institutions, including 139 patients in the training cohort and 91 patients in the validation cohort. Clinical variables and qualitative and quantitative CT features were assessed by two radiologists. CK7 positivity was defined as cytoplasmic staining in at least 10% of tumor cells. After least absolute shrinkage and selection operator regression, four machine learning models using prespecified configurations were developed in the training cohort and evaluated in the validation cohort. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, positive predictive value, negative predictive value, accuracy, F1 score, calibration analysis, and decision curve analysis. Classification thresholds were determined in the training cohort using the maximum Youden index and then applied to the validation cohort. Model stability was assessed using 1000 bootstrap resampling iterations. Results Among 230 patients, 67 had CK7-positive tumors. The final predictors included age, cystic component, corticomedullary attenuation, corticomedullary enhancement ratio, nephrographic attenuation, and tumor size. The logistic regression model was selected as the final model based on its discrimination, calibration performance, interpretability, and overall generalizability. In the validation cohort, the logistic regression model achieved an AUC of 0.714 (95% CI: 0.589, 0.828), with a sensitivity of 0.625 and a specificity of 0.627. Bootstrap resampling supported the stability of performance estimates. Conclusion This exploratory machine learning model-development study suggests that preoperatively available clinical and CT imaging features may be associated with CK7 expression in ccRCC. Further prospective validation using larger cohorts is required before clinical translation.
SN - 1471-2407
ER -