EUVIMEDEUVIMED entdecken
Crossref

Machine learning models classifiers enable a strong prediction of radioembolization-induced liver disease, and define a new bilirubin threshold for selection of patients

Itzel Rivera, Heloïse Bourien, Ewan Morel-Corlu, Alexandre Peinoit, Samuel Le Sourd, Yan Rolland iD, Etienne Garin iD, Oscar Acosta iD, Julien Edeline iD

European Journal of Nuclear Medicine and Molecular Imaging · 2026

DOI: 10.1007/s00259-026-07803-8 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Nuclear Medicine and Molecular Imaging, 2026. Verfasst von Itzel Rivera und 8 weiteren Autor:innen. Beteiligte Einrichtung: Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France. Hauptthemen laut MEDLINE: Radioembolization, Therapeutic, Machine Learning, Bilirubin, Liver Neoplasms. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 28 Literaturangaben. Gefördert von: Région Bretagne, Eugene Marquis Comprehensive Cancer Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

PURPOSE: Selective Internal Radiotherapy (SIRT) is an established treatment option for hepatocellular carcinoma (HCC). However, a major complication is radioembolization-induced liver disease (REILD). METHODS: This retrospective study, analyzed patients treated with SIRT for HCC to identify clinical factors associated with REILD and to predict treatment response. Machine learning (ML) methods were applied to two distinct cohorts to determine predictors of toxicity and response. RESULTS: Among 138 patients analyzed for REILD, ML identified bilirubin as a key predictor. A refined threshold of 26.5 µmol/L (1.55 mg/dL) was associated with toxicity risk. In the response cohort (136 patients), predictive performance was limited, nevertheless tumor dose appeared as the most frequent feature selected by the models. CONCLUSIONS: Bilirubin was confirmed as a critical factor for REILD prediction with the identification of a new threshold that may improve patient risk stratification. While tumor dose appears as the main predictor of treatment outcome, robust response models require additional features.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Radioembolization, TherapeuticMachine LearningBilirubinLiver NeoplasmsCarcinoma, HepatocellularLiver DiseasesPatient SelectionHumansFemaleMaleRetrospective StudiesPredictive Learning ModelsMiddle AgedClassification AlgorithmsAgedTreatment Outcome

Stichwörter der Autor:innen

Hepatocellular carcinomaPredictionRadioembolizationSIRTToxicityYttrium 90

Substanzen

Bilirubin

Autor:innen und Institutionen

  • Univ. Rennes, CLCC Eugène Marquis, INSERM, LTSI - UMR 1099, Rennes, F-35000, France.
  • Department of Oncology, CLCC Eugène Marquis, Rennes, 35033, France.
  • Department of Nuclear Medicine, CLCC Eugène Marquis, Rennes, 35033, France.
  • Department of Oncology, CLCC Eugène Marquis, Rennes, 35033, France. j.edeline@rennes.unicancer.fr.

ORCID-Profile: Yan Rolland, Etienne Garin, Oscar Acosta, Julien Edeline

Förderung

  • Région Bretagne
  • Eugene Marquis Comprehensive Cancer Center

Zitieren

APA

Rivera, I., Bourien, H., Morel-Corlu, E., Peinoit, A., Le Sourd, S., Rolland, Y., Garin, E., Acosta, O., & Edeline, J. (2026). Machine learning models classifiers enable a strong prediction of radioembolization-induced liver disease, and define a new bilirubin threshold for selection of patients. European Journal of Nuclear Medicine and Molecular Imaging. https://doi.org/10.1007/s00259-026-07803-8

Vancouver

Rivera I, Bourien H, Morel-Corlu E, Peinoit A, Le Sourd S, Rolland Y, et al. Machine learning models classifiers enable a strong prediction of radioembolization-induced liver disease, and define a new bilirubin threshold for selection of patients. European Journal of Nuclear Medicine and Molecular Imaging. 2026. doi:10.1007/s00259-026-07803-8

BibTeX
@article{Rivera2026,
  author = {Rivera, Itzel and Bourien, Heloïse and Morel-Corlu, Ewan and Peinoit, Alexandre and Le Sourd, Samuel and Rolland, Yan and Garin, Etienne and Acosta, Oscar and Edeline, Julien},
  title = {Machine learning models classifiers enable a strong prediction of radioembolization-induced liver disease, and define a new bilirubin threshold for selection of patients},
  journal = {European Journal of Nuclear Medicine and Molecular Imaging},
  year = {2026},
  doi = {10.1007/s00259-026-07803-8}
}
Kostenlos starten →