Email this article Prediction of recurrence-free survival in patients with renal cell carcinoma and tumor thrombosis of the renal and inferior vena cava of levels I–II using an extended Cox model and machine learning methods
- Authors: Mirzabekov M.K.1, Tikhonskii N.D.2, Shkolnik M.I.1, Bogomolov O.A.1, Trukhacheva N.V.2
-
Affiliations:
- Russian Scientific Center for Radiology and Surgical Technologies named after Academician A.M. Granov
- Altai State Medical University
- Issue: Vol 10, No 3 (2025)
- Pages: 237-242
- Section: Oncology and radiotherapy
- URL: https://journals.rcsi.science/2500-1388/article/view/312155
- DOI: https://doi.org/10.35693/SIM686422
- ID: 312155
Cite item
Abstract
Aim – to compare the predictive accuracy of Cox regression and machine learning (ML) methods regarding recurrence-free survival in patients with locally advanced renal cell carcinoma after radical treatment. Additionally, to investigate an extended Cox model in which the risk function is formed using a neural network approximator (DeepSurv).
Material and methods. This study conducted a retrospective analysis of data from patients diagnosed with renal cell carcinoma who underwent radical nephrectomy with thrombectomy from the renal and inferior vena cava between 2007 and 2024 at the Federal State Budgetary Institution “RSC for Radiology and Surgical Technologies named after Academician A.M. Granov”. The study included 100 patients (54 men and 46 women). The median age was 61.5 years (IQR: 59.7–63). Of the total observations, disease progression was recorded in 41 cases, while in the remaining 59 cases, the data were censored. The models were evaluated based on the concordance index (C-index) and interpreted using SHAP analysis.
Results. The DeepSurv neural network model demonstrated higher predictive accuracy on the test dataset compared to the classical Cox model (C-index: 0.8056 vs. 0.7917, respectively). This indicates a superior ability of DeepSurv to rank patients by individual risk of disease progression. Using SHAP analysis, the key predictors contributing most significantly to the prognosis were identified: tumor size, ISUP grade, level of tumor thrombosis, and histological tumor type. The DeepSurv model enabled the capture of complex nonlinear interactions between features, thereby improving both the interpretability and clinical applicability of the results.
Conclusion. The obtained data confirm the feasibility of using machine learning methods for personalized prognosis and optimization of monitoring strategies in patients with RCC.
Full Text
##article.viewOnOriginalSite##About the authors
Musabek K. Mirzabekov
Russian Scientific Center for Radiology and Surgical Technologies named after Academician A.M. Granov
Email: musabek.mirzabekoff@yandex.ru
ORCID iD: 0009-0003-8365-7672
postgraduate student
Russian Federation, Saint PetersburgNikolai D. Tikhonskii
Altai State Medical University
Email: wirelessm8@mail.ru
ORCID iD: 0009-0001-3077-1776
lecturer at the Department of Physics and Informatics
Russian Federation, BarnaulMikhail I. Shkolnik
Russian Scientific Center for Radiology and Surgical Technologies named after Academician A.M. Granov
Email: shkolnik_phd@mail.ru
ORCID iD: 0000-0003-0589-7999
MD, Dr. Sci. (Medicine), chief researcher, Professor
Russian Federation, Saint PetersburgOleg A. Bogomolov
Russian Scientific Center for Radiology and Surgical Technologies named after Academician A.M. Granov
Email: urologbogomolov@gmail.com
ORCID iD: 0000-0002-5860-9076
MD, Cand. Sci. (Medicine), senior researcher, Associate professor
Russian Federation, Saint PetersburgNina V. Trukhacheva
Altai State Medical University
Author for correspondence.
Email: tn10@mail.ru
ORCID iD: 0000-0002-7894-4779
Cand. Sci. (Pedagogics), Associate professor of the Department of Physics and Informatics
Russian Federation, BarnaulReferences
- Cox DR. Regression models and life tables. Journal of the Royal Statistical Society: Series B. 1972;34(2):187-220. doi: 10.1111/j.2517-6161.1972.tb00899.x
- Reva SA, Shaderkin IA, Zyatchin IV, Petrov SB. Artificial intelligence in cancer urology. Experimental and Clinical Urology. 2021;14(2):46-51. [Рева С.А., Шадеркин И.А., Зятчин И.В., и др. Искусственный интеллект в онкоурологии. Экспериментальная и клиническая урология. 2021;14(2):46-51]. doi: 10.29188/2222-8543-2021-14-2-46-51
- Du M, Haag DG, Lynch JW, et al. Comparison of the tree-based machine-learning algorithms to Cox regression in predicting the survival of oral and pharyngeal cancers: analyses based on SEER database. Cancers. 2020;12(10):2802. doi: 10.3390/cancers12102802
- Qiu X, Gao J, Yang J, et al. A comparison study of machine learning (random survival forest) and classic statistic (Cox proportional hazards) for predicting progression in high-grade glioma after proton and carbon ion radiotherapy. Frontiers in Oncology. 2020;10:551420. doi: 10.3389/fonc.2020.551420
- Lundberg SM, Lee S-I. A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems. 2017;30:4765-4774.
- Gonen M, Heller G. Concordance probability and discriminatory power in proportional hazards regression. Biometrika. 2005;92(4):965-970. doi: 10.1093/biomet/92.4.965
- Liu Y, Zhou S, Wei H, An S. A comparative study of forest methods for time-to-event data: variable selection and predictive performance. BMC Medical Research Methodology. 2021;21(1):193. doi: 10.1186/s12874-021-01386-8
- Katzman JL, Shaham U, Cloninger A, et al. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Medical Research Methodology. 2018;18(1):24. DOI: https://doi.org/10.1186/s12874-018-0482-1
- Alabi RO, Elmusrati M, Leivo I, et al. Machine-learning explainability in nasopharyngeal cancer survival using LIME and SHAP. Scientific Reports. 2023;13(1):8984. doi: 10.1038/s41598-023-35795-0
- Kantidakis G, Putter H, Lancia C, et al. Survival prediction models since liver transplantation – comparisons between Cox models and machine-learning techniques. BMC Medical Research Methodology. 2020;20(1):277. doi: 10.1186/s12874-020-01153-1
- Byun S-S, Heo TS, Choi JM, et al. Deep-learning-based prediction of prognosis in non-metastatic clear cell renal cell carcinoma. Scientific Reports. 2021;11(1):1242. doi: 10.1038/s41598-020-80262-9
- GraphPad Software. Multicollinearity in Cox proportional hazards regression. URL: https://www.graphpad.com/guides/prism/latest/statistics/stat_cox_reg_results_multicollinearity.htm
- Moncada-Torres A, van Maaren MC, Hendriks MP, et al. Explainable machine learning can outperform Cox regression predictions and provide insights in breast-cancer survival. Scientific Reports. 2021;11(1):6968. doi: 10.1038/s41598-021-86327-7
- Park H, Jeong CW, Yuk H, et al. Influence of tumor thrombus on occurrence of distant venous thromboembolism and survival in patients with renal cell carcinoma after surgery. Clinical and Applied Thrombosis/Hemostasis. 2019;25:1076029618823288. doi: 10.1177/1076029618823288
- Shin D, Lim B, Song C, et al. Comparative analysis of oncologic outcomes in surgically treated patients with renal cell carcinoma and renal-vein thrombosis by pathologic subtypes. Scientific Reports. 2025;15(1):15946. doi: 10.1038/s41598-025-00452-1
- Yang B, Liu C-X, Wu R, et al. Development and validation of a DeepSurv nomogram to predict survival outcomes and guide personalized adjuvant chemotherapy in non-small-cell lung cancer. Frontiers in Oncology. 2022;12:895014. doi: 10.3389/fonc.2022.895014
- Schulz S, Woerl A-C, Jungmann F, et al. Multimodal deep learning for prognosis prediction in renal cancer. Frontiers in Oncology. 2021;11:788740. doi: 10.3389/fonc.2021.788740
- Mahootiha M, Qadir HA, Aghayan D, et al. Deep-learning-assisted survival prognosis in renal cancer: a CT-scan-based personalized approach. Heliyon. 2024;10(2):e24374. doi: 10.1016/j.heliyon.2024.e24374
Supplementary files
