Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Nov;149(17):15855-15865.
doi: 10.1007/s00432-023-05353-2. Epub 2023 Sep 6.

Prediction of Fuhrman nuclear grade for clear cell renal carcinoma by a multi-information fusion model that incorporates CT-based features of tumor and serum tumor associated material

Yumei Zhang #  1 , Zehua Sun #  2 , Heng Ma  2 , Chenchen Wang  1 , Wei Zhang  3 , Jing Liu  4 , Min Li  5 , Yuxia Zhang  6 , Hao Guo  7 , Xinru Ba  8
Affiliations

Prediction of Fuhrman nuclear grade for clear cell renal carcinoma by a multi-information fusion model that incorporates CT-based features of tumor and serum tumor associated material

Yumei Zhang et al. J Cancer Res Clin Oncol. 2023 Nov.

Abstract

Purpose: Prediction of Fuhrman nuclear grade is crucial for making informed herapeutic decisions in clear cell renal cell carcinoma (ccRCC). The current study aimed to develop a multi-information fusion model utilizing computed tomography (CT)-based features of tumors and preoperative biochemical parameters to predict the Fuhrman nuclear grade of ccRCC in a non-invasive manner.

Methods: 218 ccRCC patients confirmed by histopathology were retrospectively analyzed. Univariate and multivariate logistic regression analyses were performed to identify independent predictors and establish a model for predicting the Fuhrman grade in ccRCC. The predictive performance of the model was evaluated using receiver operating characteristic (ROC) curves, calibration, the 10-fold cross-validation method, bootstrapping, the Hosmer-Lemeshow test, and decision curve analysis (DCA).

Results: R.E.N.A.L. Nephrometry Score (RNS) and serum tumor associated material (TAM) were identified as independent predictors for Fuhrman grade of ccRCC through multivariate logistic regression. The areas under the ROC curve (AUC) for the multi-information fusion model composed of the above two factors was 0.810, higher than that of the RNS (AUC 0.694) or TAM (AUC 0.764) alone. The calibration curve and Hosmer-Lemeshow test showed the integrated model had a good fitting degree. The 10-fold cross-validation method (AUC 0.806) and bootstrap test (AUC 0.811) showed the good stability of the model. DCA demonstrated that the model had superior clinical utility.

Conclusion: A multi-information fusion model based on CT features of tumor and routine biochemical indicators, can predict the Fuhrman grade of ccRCC using a non-invasive approach. This model holds promise for assisting clinicians in devising personalized management strategies.

Keywords: Clear cell renal cell carcinoma; Computed tomography; Fuhrman grade; Predict.

PubMed Disclaimer

Conflict of interest statement

The authors have no conflict of interest to disclose.

Figures

Fig. 1
Fig. 1
Flowchart of patients included in the study
Fig. 2
Fig. 2
Bionic volume reconstruction imaging of perirenal fat. Perirenal fat (yellow), normal renal tissue (red), and tumor (white)
Fig. 3
Fig. 3
ROC curves and calibration plot. a ROC curves for predictive models. The AUC for the integrated model was higher than the AUC for ATM alone and RNS alone. b Calibration plot. Calibration curve showed the integrated model had a good fitting degree
Fig. 4
Fig. 4
Nomogram for the prediction of high Fuhrman grade. A higher total score for each patient indicates a higher risk of a high Fuhrman grade
Fig. 5
Fig. 5
Internal validation of the predictive model. a 10-fold cross-validation. b Bootstrap test. The 10-fold cross-validation and bootstrap test showed the good stability of the model
Fig. 6
Fig. 6
DCA in the prediction of a high Fuhrman grade in ccRCC. a DCA curve. b 95% CI of the integrated model. The DCA showed that the integrated model provided a superior net benefit for threshold probabilities ranging from 0.11 to 0.89
See this image and copyright information in PMC

References

    1. Abou Heidar N, Hakam N, El-Asmar JM et al (2022) The R.E.N.A.L score’s relevance in determining perioperative and oncological outcomes: a Middle-Eastern tertiary care center experience. Arab J Urol 20(3):115–120. 10.1080/2090598X.2022.2064041 - DOI - PMC - PubMed
    1. Callahan CL, Hofmann JN, Corley DA et al (2018) Obesity and renal cell carcinoma risk by histologic subtype: a nested case-control study and meta-analysis. Cancer Epidemiol 56:31–37. 10.1016/j.canep.2018.07.002 - DOI - PMC - PubMed
    1. Camacho JC, Kokabi N, Xing M et al (2015) R.E.N.A.L. (radius, exophytic/endophytic, nearness to collecting system or sinus, anterior/posterior, and location relative to polar lines) nephrometry score predicts early tumor recurrence and complications after percutaneous ablative therapies for renal cell carcinoma: a 5-year experience. J Vasc Interv Radiol 26(5):686–693. 10.1016/j.jvir.2015.01.008 - DOI - PubMed
    1. Chang TW, Cheng WM, Fan YH et al (2021) Predictive factors for disease recurrence in patients with locally advanced renal cell carcinoma treated with curative surgery. J Chin Med Assoc 84(4):405–409. 10.1097/JCMA.0000000000000501 - DOI - PubMed
    1. Chen SH, Wu YP, Li XD et al (2017) R.E.N.A.L. nephrometry score: a preoperative risk factor predicting the Fuhrman grade of clear-cell renal carcinoma. J Cancer 8(18):3725–3732. 10.7150/jca.21189 - DOI - PMC - PubMed

MeSH terms