EUVIMEDEUVIMED entdecken
VergleichsstudieMultizentrische StudieBeobachtungsstudieOpen Access · CC BY 4.0

Predicting hepatocellular carcinoma in people with hepatitis B: a comparison between Cox proportional hazard and machine learning models

Clémence Ramier, Marie Guyomard, Camelia Protopopescu, Fabrice Carrat, Marc Bourlière, Patrizia Carrieri, Raquel Urena, ANRS/AFEF CO22 HEPATHER Study Group

Journal of Epidemiology and Population Health · 2026-08 · 74 (4) · 203387

DOI: 10.1016/j.jeph.2026.203387 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift Journal of Epidemiology and Population Health, 2026-08. Verfasst von Clémence Ramier und 7 weiteren Autor:innen. Beteiligte Einrichtung: Aix Marseille Univ, INSERM, IRD, SESSTIM, Sciences Économiques & Sociales de la Santé & Traitement de l'Information Médicale, ISSPAM, Marseille, Fran…. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Hepatitis B, Chronic, Liver Neoplasms, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bristol-Myers Squibb Company, MSD France SAS, French National Research Agency.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND AIM: Hepatocellular carcinoma (HCC) is a leading cause of cancer-related death worldwide, with chronic hepatitis B virus (HBV) infection being a major risk factor. To date, existing predictive scores of HCC are mainly based on traditional Cox proportional hazard (CPH) models. This study aimed to compare the variable selection process and performance of CPH models with those of machine learning (ML) and deep learning (DL) algorithms in predicting HCC among patients with chronic HBV infection. METHODS: We used data from 4,370 individuals with chronic HBV infection enrolled in the French prospective multicentre ANRS CO22 HEPATHER cohort, of which 56 (1.3%) developed an HCC. Two published CPH-based scores (ADAPTT and SADAPTT) were compared to Random Survival Forest (RSF), Survival Support Vector Machine (SVM), Survival XGBoost, and DeepSurv algorithms. Models were evaluated using Harrell's C-index, Inverse-Probability-of-Censoring Weighting win ratio statistic, and time-dependent area under the ROC curve at 3, 5, and 8 years. The same set of covariables was used to build all the models. RESULTS: CPH models demonstrated similar or higher performances (C-index [95% confidence interval]: 0.84 [0.82-0.85]) for HCC prediction compared to ML and DL models, with less overfitting. Survival SVM and RSF performed similarly (0.81 [0.79-0.83] and 0.81 [0.79-0.82], respectively) without outperforming CPH models. Variable selection was consistent across top-performing models, though CPH models more effectively captured the predictive value of certain behavioural factors, such as soft drink intake. CONCLUSIONS: In this dataset with a limited sample size and strongly imbalanced outcome, traditional CPH models provided robust, interpretable, and computationally efficient predictions for HCC risk. ML and DL methods did not outperform traditional models, reinforcing the validity of traditional statistical approaches in small to medium datasets.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, HepatocellularHepatitis B, ChronicLiver NeoplasmsMachine LearningPredictive Learning ModelsAdultFemaleHumansMaleMiddle AgedBoosting Machine Learning AlgorithmsFrancePrediction AlgorithmsProportional Hazards ModelsProspective StudiesRandom ForestRisk Factors

Stichwörter der Autor:innen

Cox modelsDeepSurvLiver cancerMachine learningRandom Forest

Autor:innen und Institutionen

  • Aix Marseille Univ, INSERM, IRD, SESSTIM, Sciences Économiques & Sociales de la Santé & Traitement de l'Information Médicale, ISSPAM, Marseille, France.
  • Aix Marseille Univ, INSERM, IRD, SESSTIM, Sciences Économiques & Sociales de la Santé & Traitement de l'Information Médicale, ISSPAM, Marseille, France. Electronic address: camelia.protopopescu@inserm.fr.
  • Institut National de la Santé et de la Recherche Médicale (INSERM), Institut Pierre Louis d'Epidémiologie et de Santé Publique, Sorbonne Université, Paris, France; Hôpital Saint-Antoine, Unité de Santé Publique, Assista…
  • Aix Marseille Univ, INSERM, IRD, SESSTIM, Sciences Économiques & Sociales de la Santé & Traitement de l'Information Médicale, ISSPAM, Marseille, France; Département d'hépatologie et gastroentérologie, Hôpital Saint Jose…

Förderung

  • Bristol-Myers Squibb Company
  • MSD France SAS
  • French National Research Agency
  • AbbVie Inc
  • Gilead Sciences Inc
  • F. Hoffmann-La Roche Ltd

Zitieren

APA

Ramier, C., Guyomard, M., Protopopescu, C., Carrat, F., Bourlière, M., Carrieri, P., Urena, R., & ANRS/AFEF CO22 HEPATHER Study Group (2026). Predicting hepatocellular carcinoma in people with hepatitis B: a comparison between Cox proportional hazard and machine learning models. Journal of Epidemiology and Population Health, 74(4), 203387. https://doi.org/10.1016/j.jeph.2026.203387

Vancouver

Ramier C, Guyomard M, Protopopescu C, Carrat F, Bourlière M, Carrieri P, et al. Predicting hepatocellular carcinoma in people with hepatitis B: a comparison between Cox proportional hazard and machine learning models. Journal of Epidemiology and Population Health. 2026;74(4):203387. doi:10.1016/j.jeph.2026.203387

BibTeX
@article{Ramier2026,
  author = {Ramier, Clémence and Guyomard, Marie and Protopopescu, Camelia and Carrat, Fabrice and Bourlière, Marc and Carrieri, Patrizia and Urena, Raquel and ANRS/AFEF CO22 HEPATHER Study Group, ANRS/AFEF CO22 HEPATHER Study Group},
  title = {Predicting hepatocellular carcinoma in people with hepatitis B: a comparison between Cox proportional hazard and machine learning models},
  journal = {Journal of Epidemiology and Population Health},
  year = {2026},
  volume = {74},
  number = {4},
  pages = {203387},
  doi = {10.1016/j.jeph.2026.203387}
}
Kostenlos starten →