0 63

Cited 1 times in

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

 Hye Won Lee  ;  Hwiyoung Kim  ;  Taeyun Park  ;  Soo Young Park  ;  Young Eun Chon  ;  Yeon Seok Seo  ;  Jae Seung Lee  ;  Jun Yong Park  ;  Do Young Kim  ;  Sang Hoon Ahn  ;  Beom Kyung Kim  ;  Seung Up Kim 
 LIVER INTERNATIONAL, Vol.43(8) : 1813-1821, 2023-08 
Journal Title
Issue Date
Antiviral Agents / therapeutic use ; Carcinoma, Hepatocellular* / drug therapy ; Carcinoma, Hepatocellular* / epidemiology ; Carcinoma, Hepatocellular* / etiology ; Female ; Hepatitis B, Chronic* / complications ; Hepatitis B, Chronic* / drug therapy ; Hepatitis B, Chronic* / epidemiology ; Humans ; Liver Neoplasms* / drug therapy ; Liver Neoplasms* / epidemiology ; Liver Neoplasms* / etiology ; Male ; Middle Aged ; Retrospective Studies ; Tenofovir / therapeutic use
antiviral therapy ; chronic hepatitis B ; entecavir ; hepatocellular carcinoma ; machine learning ; performance ; prediction ; prognosis ; risk prediction ; tenofovir
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.
Full Text
Appears in Collections:
1. College of Medicine (의과대학) > Dept. of Biomedical Systems Informatics (의생명시스템정보학교실) > 1. Journal Papers
1. College of Medicine (의과대학) > Dept. of Internal Medicine (내과학교실) > 1. Journal Papers
Yonsei Authors
Kim, Do Young(김도영)
Kim, Beom Kyung(김범경) ORCID logo https://orcid.org/0000-0002-5363-2496
Kim, Seung Up(김승업) ORCID logo https://orcid.org/0000-0002-9658-8050
Kim, Hwiyoung(김휘영)
Park, Jun Yong(박준용) ORCID logo https://orcid.org/0000-0001-6324-2224
Ahn, Sang Hoon(안상훈) ORCID logo https://orcid.org/0000-0002-3629-4624
Lee, Jae Seung(이재승) ORCID logo https://orcid.org/0000-0002-2371-0967
Lee, Hye Won(이혜원) ORCID logo https://orcid.org/0000-0002-3552-3560
사서에게 알리기


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.