AccScience Publishing / EJMO / Online First / DOI: 10.36922/EJMO026310393
Cite this article
1
Download
23
Views
Related Info Links
More by Authors Links
Journal Browser
Volume | Year
Issue
Search
News and Announcements
View All
ORIGINAL RESEARCH ARTICLE

An integrated clinical risk scoring and machine learning framework for risk stratification of hepatocellular carcinoma: Development and real-world clinical validation

Yingying Luo1† ,  Zengbei Yuan2† ,  Yingkang Lin3† ,  XiaoLei Huang1 ,  Feiyang Pu4 ,  Rui Li1 ,  Lihong Liu1* ,  Zhihua Ni1*
Show Less
1 Department of Radiology, Shanghai Baoshan Hospital of Integrated Traditional Chinese and Western Medicine, Shanghai , China
2 School of Medical Technology and Engineering, Fujian Medical University, Fuzhou, Fujian , China
3 Department of Rehabilitation, Guangdong Work Injury Rehabilitation Hospital, Guangzhou, Guangdong , China
4 Department of Nuclear Medicine, Shanghai Pulmonary Hospital, Tongji University School of Medicine, Shanghai , China
†These authors contributed equally to this work.
Received: 28 July 2026 | Revised: 10 September 2026 | Accepted: 17 September 2026 | Published online: 16 November 2026
© 2026 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

Introduction: Hepatocellular carcinoma (HCC) remains a major cause of cancer-related mortality, highlighting the need for more accurate risk stratification approaches.

Objective: To develop and validate an integrated clinical risk scoring (CRS) and machine learning (ML) system to accurately identify HCC, overcoming the limitations of traditional alpha-fetoprotein (AFP) screening, especially in AFP-negative individuals.

Methods: A retrospective cross-sectional diagnostic study utilized data from two institutions (development cohort n = 5,000; external validation cohort n = 443) with 12 routine clinical variables. Multivariable logistic regression was used to construct the CRS, and ensemble ML models were developed. Performance was assessed via area under the receiver operating characteristic curve (AUC), quantitative calibration measures, decision curve analysis (DCA), net reclassification improvement (NRI), and integrated discrimination improvement (IDI). We applied development-trained models directly to the independent cohort for strict external validation.

Results: Hepatitis C, diabetes and hepatitis B were identified as the strongest independent risk factors for HCC. In the development cohort, the CatBoost model demonstrated the best overall discriminatory ability (AUC = 0.9773), significantly outperforming the single AFP indicator (0.6377) and CRS (0.9385); notably, in the independent validation cohort, CRS demonstrated superior stability in terms of AUC (0.9849) and risk reclassification ability (NRI/IDI), performing slightly better than CatBoost (AUC = 0.9816). DCA, NRI, and IDI confirmed significant incremental clinical net benefit and risk reclassification over AFP-only screening (p < 0.001).

Conclusion: This integrated HCC risk stratification system effectively overcomes traditional AFP screening limitations, particularly in AFP-negative populations. The observed bias-variance trade-off supports a tiered deployment strategy: CRS for robust screening in resource-limited settings, and ML for precision assessment in well-resourced centers.

Keywords
Hepatocellular carcinoma
Machine learning
Clinical risk scoring
Alpha-fetoprotein
Funding
None.
Conflict of interest
This work was supported by the Science and Technology Innovation Special Fund Project of Shanghai Baoshan District Science and Technology Committee (2023-E-17) and the Excellent Youth Program of Shanghai Baoshan District Health Committee (BSWSYC-2023-04).
References
  1. Lee DD, Croome KP, Musto KR, et al. Liver transplantation for intrahepatic cholangiocarcinoma. Liver Transpl. 2018;24(5):634-644. doi: 10.1002/lt.25052
  2. Sung H, Filho AM, Laversanne M, et al. Global cancer statistics 2024: GLOBOCAN estimates of incidence and mortality worldwide for 34 cancers in 186 countries. CA Cancer J Clin. 2026;76(4). doi: 10.3322/caac.70090
  3. Han B, Zheng R, Zeng H, et al. Cancer incidence and mortality in China, 2022. J Natl Cancer Cent. 2024;4(1):47-53. doi: 10.1016/j.jncc.2024.01.006
  4. Zhou J, Sun H, Wang Z, et al. Guidelines for the diagnosis and treatment of primary liver cancer (2022 edition). Liver Cancer. 2023;12(5):405-444. doi: 10.1159/000530495
  5. de Lope CR, Tremosini S, Forner A, Reig M, Bruix J. Management of HCC. J Hepatol. 2012;56(suppl 1):S75-S87. doi: 10.1016/S0168-8278(12)60009-9
  6. Tzartzeva K, Obi J, Rich NE, et al. Surveillance imaging and alpha fetoprotein for early detection of hepatocellular carcinoma in patients with cirrhosis: a meta-analysis. Gastroenterology. 2018;154(6):1706-1718.e1. doi: 10.1053/j.gastro.2018.01.064
  7. Hanif H, Ali MJ, Susheela AT, et al. Update on the applications and limitations of alpha-fetoprotein for hepatocellular carcinoma. World J Gastroenterol. 2022;28(2):216-229. doi: 10.3748/wjg.v28.i2.216
  8. Turshudzhyan A, Wu GY. Persistently rising alpha-fetoprotein in the diagnosis of hepatocellular carcinoma: a review. J Clin Transl Hepatol. 2022;10(1):159-163. doi: 10.14218/JCTH.2021.00176
  9. Galle PR, Forner A, Llovet JM, et al. EASL Clinical Practice Guidelines: management of hepatocellular carcinoma. J Hepatol. 2018;69(1):182-236. doi: 10.1016/j.jhep.2018.03.019
  10. Osho A, Rich NE, Singal AG. Role of imaging in management of hepatocellular carcinoma: surveillance, diagnosis, and treatment response. Hepatoma Res. 2020;6:55. doi: 10.20517/2394-5079.2020.42
  11. Shan S, Jia J. The clinical management of hepatocellular carcinoma in China: progress and challenges. Clin Mol Hepatol. 2023;29(2):339-341. doi: 10.3350/cmh.2023.0077
  12. Chang YP, Chen YC, Liu CH. Risk scores for stratifying hepatocellular carcinoma and optimizing surveillance strategies. Cancers (Basel). 2026;18(1):158. doi: 10.3390/cancers18010158
  13. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56. doi: 10.1038/s41591-018-0300-7
  14. Zou ZM, Chang DH, Liu H, Xiao YD. Current updates in machine learning in the prediction of therapeutic outcome of hepatocellular carcinoma: what should we know? Insights Imaging. 2021;12(1). doi: 10.1186/s13244-021-00977-9
  15. Liu W, Wei R, Chen J, et al. Prognosis prediction and risk stratification of transarterial chemoembolization or intraarterial chemotherapy for unresectable hepatocellular carcinoma based on machine learning. Eur Radiol. 2024;34(8):5094-5107. doi: 10.1007/s00330-024-10581-2
  16. Zhang Y, Tong S, Yang J, et al. Explainable machine learning model for predicting the transarterial chemoembolization response and subtypes of hepatocellular carcinoma patients. BMC Gastroenterol. 2025;25(1). doi: 10.1186/s12876-025-04105-5
  17. Xu Y, Zhang B, Zhou F, et al. Development of machine learning-based personalized predictive models for risk evaluation of hepatocellular carcinoma in hepatitis B virus-related cirrhosis patients with low levels of serum alpha-fetoprotein. Ann Hepatol. 2024;29(6):101540. doi: 10.1016/j.aohep.2024.101540
  18. Collins GS, Reitsma JB, Altman DG, Moons KG. Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis (TRIPOD): the TRIPOD statement. Ann Intern Med. 2015;162(1):55-63. doi: 10.7326/M14-0697
  19. Van Calster B, Steyerberg EW, Wynants L, van Smeden M. There is no such thing as a validated prediction model. BMC Med. 2023;21(1). doi: 10.1186/s12916-023-02779-w
  20. Imperiale TF, Monahan PO. Risk stratification strategies for colorectal cancer screening: from logistic regression to artificial intelligence. Gastrointest Endosc Clin N Am. 2020;30(3):423-440. doi: 10.1016/j.giec.2020.02.004
  21. Ghuriani V, Wassan JT, Tripathi P, Chauhan A. XGB-BIF: an XGBoost-driven biomarker identification framework for detecting cancer using human genomic data. Int J Mol Sci. 2025;26(12):5590. doi: 10.3390/ijms26125590
  22. Wu J, Tao G, Xie S, Yang H, Qi F, Bao N, et al. Prediction of three-year all-cause mortality in patients with heart failure and atrial fibrillation using the CatBoost model. BMC Cardiovasc Disord. 2025;25(1). doi: 10.1186/s12872-025-04928-w
  23. Huang C, Fang M, Feng H, et al. N-glycan fingerprint predicts alpha-fetoprotein negative hepatocellular carcinoma: a large-scale multicenter study. Int J Cancer. 2021;149(3):717-727. doi: 10.1002/ijc.33564
  24. Pencina MJ, D’Agostino RB Sr, D’Agostino RB Jr, Vasan RS. Evaluating the added predictive ability of a new marker: from area under the ROC curve to reclassification and beyond. Stat Med. 2008;27(2):157-172. doi: 10.1002/sim.2929
  25. Kalligeros M, Henry L, Younossi ZM. Metabolic dysfunction-associated steatotic liver disease and its link to cancer. Metabolism. 2024;160:156004. doi: 10.1016/j.metabol.2024.156004
Share
Back to top
Eurasian Journal of Medicine and Oncology, Electronic ISSN: 2587-196X Print ISSN: 2587-2400, Published by AccScience Publishing