A machine learning model for predicting hepatocellular carcinoma risk in patients with chronic hepatitis B - PubMed (original) (raw)

. 2023 Aug;43(8):1813-1821.

doi: 10.1111/liv.15597.

Hye Won Lee 1 2 3, Taeyun Park 5, Soo Young Park 6, Young Eun Chon 7, Yeon Seok Seo 8, Jae Seung Lee 1 2 3, Jun Yong Park 1 2 3, Do Young Kim 1 2 3, Sang Hoon Ahn 1 2 3, Beom Kyung Kim 1 2 3, Seung Up Kim 1 2 3

Affiliations

A machine learning model for predicting hepatocellular carcinoma risk in patients with chronic hepatitis B

Hye Won Lee et al. Liver Int. 2023 Aug.

Abstract

Background: Machine learning (ML) algorithms can be used to overcome the prognostic performance limitations of conventional hepatocellular carcinoma (HCC) risk models. We established and validated an ML-based HCC predictive model optimized for patients with chronic hepatitis B (CHB) infections receiving antiviral therapy (AVT).

Methods: Treatment-naïve CHB patients who were started entecavir (ETV) or tenofovir disoproxil fumarate (TDF) were enrolled. We used a training cohort (n = 960) to develop a novel ML model that predicted HCC development within 5 years and validated the model using an independent external cohort (n = 1937). ML algorithms consider all potential interactions and do not use predefined hypotheses.

Results: The mean age of the patients in the training cohort was 48 years, and most patients (68.9%) were men. During the median 59.3 (interquartile range 45.8-72.3) months of follow-up, 69 (7.2%) patients developed HCC. Our ML-based HCC risk prediction model had an area under the receiver-operating characteristic curve (AUC) of 0.900, which was better than the AUCs of CAMD (0.778) and REAL B (0.772) (both p < .05). The better performance of our model was maintained (AUC = 0.872 vs. 0.788 for CAMD and 0.801 for REAL B) in the validation cohort. Using cut-off probabilities of 0.3 and 0.5, the cumulative incidence of HCC development differed significantly among the three risk groups (p < .001).

Conclusions: Our new ML model performed better than models in terms of predicting the risk of HCC development in CHB patients receiving AVT.

Keywords: antiviral therapy; chronic hepatitis B; entecavir; hepatocellular carcinoma; machine learning; performance; prediction; prognosis; risk prediction; tenofovir.

© 2023 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

PubMed Disclaimer

References

REFERENCES

    1. Fattovich G, Bortolotti F, Donato F. Natural history of chronic hepatitis B: special emphasis on disease progression and prognostic factors. J Hepatol. 2008;48:335-352.
    1. Chen CJ, Yang HI, Su J, et al. Risk of hepatocellular carcinoma across a biological gradient of serum hepatitis B virus DNA level. Jama. 2006;295:65-73.
    1. Russo FP, Rodríguez-Castro K, Scribano L, Gottardo G, Vanin V, Farinati F. Role of antiviral therapy in the natural history of hepatitis B virus-related chronic liver disease. World J Hepatol. 2015;7:1097-1104.
    1. Tseng T-C. Another oral antiviral treatment, but still far away from hepatitis B virus cure. Clin Mol Hepatol. 2021;27:281-282.
    1. Papatheodoridis GV, Chan HL, Hansen BE, Janssen HL, Lampertico P. Risk of hepatocellular carcinoma in chronic hepatitis B: assessment and modification with current antiviral therapy. J Hepatol. 2015;62:956-967.

Publication types

MeSH terms

Substances

LinkOut - more resources