International Journal of Medical and All Body Health Research  |  e-ISSN: 2582-8940  |  Double-Blind Peer Review  |  Open Access  |  CC BY-NC-SA 4.0

Current Issues
     2026:7/4

International Journal of Medical and All Body Health Research

e-ISSN: 2582-8940 | Open Access

Explainable Cox‑Ridge Survival Modeling with SHAP for Early Risk Stratification After Transarterial Chemoembolization in Hepatocellular Carcinoma: A Multicenter Analysis

Zaffar Abbas, Imran Muhammad

Qingdao University, China; Organ Transplantation Center, The Affiliated Hospital of Qingdao University Qingdao, Shandong, China

Article Information

Volume / Issue7 / 2 (April-June 2026)
Pages151-160
AccessOpen Access

Publication Timeline

  • Received19 March 2026
  • Accepted18 April 2026
  • Published

Full Text (PDF)

Open Access - Free to Download

Download Full Article (PDF) JATS XML

Abstract

Purpose: The aim of this study is to create and validate an actionable interpretable survival model of hepatocellular carcinoma patients receiving Transarterial chemoembolization, by combining clinical data and CT radiomic data under a SHAP framework.
Materials and Methods: In the analysis, the publicly available WAW-TACE cohort (N = 233; 170 deaths, cadaveric data access group) was used. Of the 3,339 radiomics features, the 100 with the highest variance were selected. Following the preprocessing and one-hot encoding (features that did not converge were assigned non-significant p-values) and based on univariate Cox regression analysis, the 30 top- ranked predictors were selected. To perform the survival model, a ridge-penalized Cox proportional hazards with an α = 20, and 5-fold cross validation, was used to fit 70% of the data and the remaining 30% was used to evaluate the model. The performance of the model was evaluated using the Harrell's C-index and a time dependent AUC (Uno et al., 2013). 12-month calibration was performed along with an optimism correction (200 bootstrap iterations). Interpretability of the survival model was done using SHAP (Kernel Explainer).
Results: The test C-index was 0.654 (95% CI: 0.592–0.698). The internal bootstrap corrected C-index, reflecting a correction for optimism at a sample out of the distribution, was 0.728. The time- dependent AUC was noted at 0.874 (6 months), 0.803 (12 months), 0.663 (24 months), and 0.634 (36 months). The top predictors included serum albumin, number of lesions, and being female. The trained model had a higher C-index compared to the Hepatocellular carcinoma, Albumin, and Prothrombin Time-based Assessment of Liver Function and Risk of Death (HAP) score (C-index: 0.544) and the Assessment of Liver Function and Risk of Death (ALBI-TAE) (C-index: 0.624). Risk separation was significant and improved using the median risk threshold. The SHAP analysis presented plausible feature interactions and provided exogenous explanations.
Conclusion: The development of an explainable Cox-ridge model has established significant short-term survival prediction after TACE for HCC. The SHAP-based explanations provided for the model suggest that it can be incorporated into clinical decision support pathways with early clinical triage to facilitate access to systemic therapy.
 

Keywords

Hepatocellular carcinomaTransarterial chemoembolizationRadiomicsCox proportional hazards modelSHAP explainable AI

References

  1. Sung H, Ferlay J, Siegel RL, Laversanne M, Soerjomataram I, Jemal A, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2021;71(3):209-49. [Google Scholar][Crossref]
  2. Villanueva A. Hepatocellular carcinoma. N Engl J Med. 2019;380(15):1450-62. [Google Scholar][Crossref]
  3. Chen W, Zheng R, Baade PD, Zhang S, Zeng H, Bray F, et al. Cancer statistics in China, 2015. CA Cancer J Clin. 2016;66(2):115-32. [Google Scholar][Crossref]
  4. Llovet JM, Kelley RK, Villanueva A, Singal AG, Pikarsky E, Roayaie S, et al. Hepatocellular carcinoma. Nat Rev Dis Primers. 2021;7(1):6. [Google Scholar][Crossref]
  5. Kudo M, Ueshima K, Ikeda M, Torimura T, Tanabe N, Aikata H, et al. Randomised, multicentre prospective trial of transarterial chemoembolisation (TACE) plus sorafenib as compared with TACE alone in patients with International Journal of Medical and All Body Health Research www.allmedicaljournal.com hepatocellular carcinoma: TACTICS trial. Gut. 2020;69(8):1492-501. [Google Scholar][Crossref]
  6. Finn RS, Qin S, Ikeda M, Galle PR, Ducreux M, Kim TY, et al. Atezolizumab plus bevacizumab in unresectable hepatocellular carcinoma. N Engl J Med. 2020;382(20):1894-905. [Google Scholar][Crossref]
  7. Llovet JM, Singal AG, Villanueva A, Finn RS, Kudo M, Galle PR, et al. Prognostic and predictive factors in patients with advanced HCC and elevated alpha-fetoprotein treated with ramucirumab in two randomized phase III trials. Clin Cancer Res. 2022;28(11):2297-305. [Google Scholar][Crossref]
  8. Izzo C, Annunziata M, Melara G, Sciorio R, Dallio M, Masarone M, et al. The role of resveratrol in liver disease: a comprehensive review from in vitro to clinical trials. Nutrients. 2021;13(3):933. [Google Scholar][Crossref]
  9. Li G, Li X, Mahmud I, Ysaguirre J, Fekry B, Wang S, et al. Interfering with lipid metabolism through targeting CES1 sensitizes hepatocellular carcinoma for chemotherapy. JCI Insight. 2023;8(2):e163624. [Google Scholar][Crossref]
  10. Ishwaran H, Kogalur UB, Blackstone EH, Lauer MS. Random survival forests. Ann Appl Stat. 2008;2(3):841-60. [Google Scholar][Crossref]
  11. Katzman JL, Shaham U, Cloninger A, Bates J, Jiang T, Kluger Y. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med Res Methodol. 2018;18(1):24. [Google Scholar][Crossref]
  12. Watson DS, Krutzinna J, Bruce IN, Griffiths CE, McInnes IB, Barnes MR, et al. Clinical applications of machine learning algorithms: beyond the black box. BMJ. 2019;364:l886. [Google Scholar][Crossref]
  13. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. [Google Scholar][Crossref]
  14. Lundberg S, Lee SI. A unified approach to interpreting model predictions. In: Guyon I, Luxburg UV, Bengio S, Wallach H, Fergus R, Vishwanathan S, et al., editors. Advances in Neural Information Processing Systems 30. New York (NY): Curran Associates Inc.; 2017. p. 4765-74. [Google Scholar][Crossref]
  15. Lundberg SM, Erion G, Chen H, DeGrave A, Prutkin JM, Nair B, et al. From local explanations to global understanding with explainable AI for trees. Nat Mach Intell. 2020;2(1):56-67. [Google Scholar][Crossref]
  16. Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Brief Bioinform. 2018;19(6):1236-46. [Google Scholar][Crossref]
  17. Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, Van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441-6. [Google Scholar][Crossref]
  18. Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278(2):563-77. [Google Scholar][Crossref]
  19. Aerts HJWL, Velazquez ER, Leijenaar RTH, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014;5:4006. [Google Scholar][Crossref]
  20. Rizzo S, Botta F, Raimondi S, Origgi D, Fanciullo C, Morganti AG, et al. Radiomics: the facts and the challenges of image analysis. Eur Radiol Exp. 2018;2(1):36. [Google Scholar][Crossref]
  21. Peduzzi P, Concato J, Feinstein AR, Holford TR. Importance of events per independent variable in proportional hazards regression analysis. II. Accuracy and precision of regression estimates. J Clin Epidemiol. 1995;48(12):1503-10. [Google Scholar][Crossref]
  22. Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJWL. Machine learning methods for quantitative radiomic biomarkers. Sci Rep. 2015;5:13087. [Google Scholar][Crossref]
  23. Pruinelli L, Balakrishnan K, Ma S, Li Z, Wall A, Lai JC, et al. Transforming liver transplant allocation with artificial intelligence and machine learning: a systematic review. BMC Med Inform Decis Mak. 2025;25(1):98. [Google Scholar][Crossref]
  24. Harrell FE Jr, Lee KL, Mark DB. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Stat Med. 1996;15(4):361-87. [Google Scholar][Crossref]
  25. Uno H, Cai T, Tian L, Wei LJ. Evaluating prediction rules for t-year survivors with censored regression models. J Am Stat Assoc. 2007;102(478):527-37. [Google Scholar][Crossref]
  26. Efron B, Tibshirani RJ. An introduction to the bootstrap. New York (NY): Chapman and Hall/CRC; 1993. [Google Scholar][Crossref]
  27. Molnar C. Interpretable machine learning. 2nd ed. Munich: Leanpub; 2022. [Google Scholar][Crossref]
  28. Molnar C, Freiesleben T, König G, Herbinger J, Reisinger T, Casalicchio G, et al. Relating the partial dependence plot and permutation feature importance to the data generating process. In: World Conference on Explainable Artificial Intelligence; 2023. Cham: Springer; 2023. [Google Scholar][Crossref]
  29. Llovet JM, Castet F, Heikenwalder M, Maini MK, Mazzaferro V, Pinato DJ, et al. Immunotherapies for hepatocellular carcinoma. Nat Rev Clin Oncol. 2022;19(3):151-72. [Google Scholar][Crossref]
  30. Johnson PJ, Berhane S, Kagebayashi C, Satomura S, Teng M, Reeves HL, et al. Assessment of liver function in patients with hepatocellular carcinoma: a new evidence-based approach—the ALBI grade. J Clin Oncol. 2015;33(6):550-8. [Google Scholar][Crossref]
  31. Zhu D, Ciais P, Krinner G, Maignan F, Jornet Puig A, Hugelius G. Controls of soil organic matter on soil thermal dynamics in the northern high latitudes. Nat Commun. 2019;10(1):3172. [Google Scholar][Crossref]
  32. Kocher M, Ruge MI, Galldiks N, Lohmann P. Applications of radiomics and machine learning for radiotherapy of malignant brain tumors. Strahlenther Onkol. 2020;196(10):856-67. [Google Scholar][Crossref]
  33. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17(1):195. [Google Scholar][Crossref]

How to Cite

Abbas, Z., & Muhammad, I. (2026). Explainable Cox‑Ridge Survival Modeling with SHAP for Early Risk Stratification After Transarterial Chemoembolization in Hepatocellular Carcinoma: A Multicenter Analysis. International Journal of Medical and All Body Health Research, 7(2), 151-160. https://doi.org/10.54660/IJMBHR.2026.7.2.151-160

Abbas, Zaffar, and Imran Muhammad. "Explainable Cox‑Ridge Survival Modeling with SHAP for Early Risk Stratification After Transarterial Chemoembolization in Hepatocellular Carcinoma: A Multicenter Analysis." International Journal of Medical and All Body Health Research, vol. 7, no. 2, 2026, pp. 151-160. https://doi.org/10.54660/IJMBHR.2026.7.2.151-160.

Abbas, Z. and Muhammad, I. (2026) 'Explainable Cox‑Ridge Survival Modeling with SHAP for Early Risk Stratification After Transarterial Chemoembolization in Hepatocellular Carcinoma: A Multicenter Analysis', International Journal of Medical and All Body Health Research, 7(2), pp. 151-160. doi: 10.54660/IJMBHR.2026.7.2.151-160.

Abbas Z, Muhammad I. Explainable Cox‑Ridge Survival Modeling with SHAP for Early Risk Stratification After Transarterial Chemoembolization in Hepatocellular Carcinoma: A Multicenter Analysis. International Journal of Medical and All Body Health Research. 2026;7(2):151-160. doi:10.54660/IJMBHR.2026.7.2.151-160

Similar Articles

Share

Find this Article on

Google Scholar Semantic Scholar OpenAlex Scilit Crossref ResearchGate BASE

A newly published article may take a few days to appear on these services.