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