EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY 4.0

Integrating Machine Learning and Follow-Up Variables to Improve Early Detection of Hepatocellular Carcinoma in Tyrosinemia Type 1: A Multicenter Study

Karen Fuenzalida iD, María Jesús Leal-Witt iD, Alejandro Acevedo, Manuel Muñoz, Camila Gudenschwager iD, Carolina Arias, Juan Francisco Cabello, Giancarlo La Marca, Cristiano Rizzo, Andrea Pietrobattista iD, Marco Spada, Carlo Dionisi-Vici iD und 1 weitere

International Journal of Molecular Sciences · 2025

DOI: 10.3390/ijms26083839 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift International Journal of Molecular Sciences, 2025. Verfasst von Karen Fuenzalida und 12 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Genetic and Metabolic Diseases, Institute of Nutrition and Food Technology INTA, University of Chile, Av. El Libano 5524, Santiago 7830…. Hauptthemen laut MEDLINE: Carcinoma, Hepatocellular, Tyrosinemias, Machine Learning, Liver Neoplasms. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Agencia Nacional de Investigación y Desarrollo (ANID), Laboratory of Genetic and Metabolic Disease, INTA, University of Chile.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Hepatocellular carcinoma (HCC) is a major complication of tyrosinemia type 1 (HT-1), an inborn error of metabolism affecting tyrosine catabolism. The risk of HCC is higher in late diagnoses despite treatment. Alpha-fetoprotein (AFP) is widely used to detect liver cancer but has limitations in early-stage HCC detection. This study aimed to implement a machine-learning (ML) approach to identify the most relevant laboratory variables to predict AFP alteration using constrained multidimensional data from Chilean and Italian HT-1 cohorts. A longitudinal retrospective study analyzed 219 records from 35 HT-1 patients, including 8 with HCC and 5 diagnosed through newborn screening. The dataset contained biochemical and demographic variables that were analyzed using the eXtreme Gradient Boosting algorithm, which was trained to predict abnormal AFP levels (>5 ng/mL). Four key variables emerged as significant predictors: alanine transaminase (ALT), alkaline phosphatase, age at diagnosis, and current age. ALT emerged as the most promising indicator of AFP alteration, potentially preceding AFP level changes and improving HCC detection specificity at a cut-off value of 29 UI/L (AUROC = 0.73). Despite limited data from this rare disease, the ML approach successfully analyzed follow-up biomarkers, identifying ALT as an early predictor of AFP elevation and a potential biomarker for HCC progression.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, HepatocellularTyrosinemiasMachine LearningLiver NeoplasmsEarly Detection of CancerHumansMaleFemalealpha-FetoproteinsRetrospective StudiesAdultMiddle AgedInfant, NewbornInfantFollow-Up StudiesAlanine TransaminaseBiomarkers, TumorChild, PreschoolAdolescentChildAlkaline PhosphataseYoung AdultLongitudinal Studies

Stichwörter der Autor:innen

alpha-fetoproteinartificial intelligencehepatocellular carcinomahereditary tyrosinemia type 1inborn errors of metabolismliver biomarkers

Substanzen

alpha-FetoproteinsAlanine TransaminaseBiomarkers, TumorAlkaline Phosphatase

Autor:innen und Institutionen

  • Laboratory of Genetic and Metabolic Diseases, Institute of Nutrition and Food Technology INTA, University of Chile, Av. El Libano 5524, Santiago 7830490, Chile.
  • Meyer Children's Hospital IRCCS, Viale Gaetano Pieraccini, 24, 50139 Florence, Italy.
  • Department of Experimental and Clinical Biomedical Sciences, University of Florence, Largo Brambilla, 3, 50134 Florence, Italy.
  • Division of Metabolic Diseases and Hepatology, Ospedale Pediatrico Bambino Gesù IRCCS, 00165 Rome, Italy.
  • Division of Abdominal Transplantation, Hepato-Bilio-Pancreatic Surgery Unit, Ospedale Pediatrico Bambino Gesù IRCCS, 00165 Rome, Italy.

ORCID-Profile: Karen Fuenzalida, María Jesús Leal-Witt, Camila Gudenschwager, Andrea Pietrobattista, Carlo Dionisi-Vici, Verónica Cornejo

Förderung

  • Agencia Nacional de Investigación y Desarrollo (ANID)
  • Laboratory of Genetic and Metabolic Disease, INTA, University of Chile

Zitieren

APA

Fuenzalida, K., Leal-Witt, M. J., Acevedo, A., Muñoz, M., Gudenschwager, C., Arias, C., Cabello, J. F., La Marca, G., Rizzo, C., Pietrobattista, A., Spada, M., Dionisi-Vici, C., & Cornejo, V. (2025). Integrating Machine Learning and Follow-Up Variables to Improve Early Detection of Hepatocellular Carcinoma in Tyrosinemia Type 1: A Multicenter Study. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms26083839

Vancouver

Fuenzalida K, Leal-Witt MJ, Acevedo A, Muñoz M, Gudenschwager C, Arias C, et al. Integrating Machine Learning and Follow-Up Variables to Improve Early Detection of Hepatocellular Carcinoma in Tyrosinemia Type 1: A Multicenter Study. International Journal of Molecular Sciences. 2025. doi:10.3390/ijms26083839

BibTeX
@article{Fuenzalida2025,
  author = {Fuenzalida, Karen and Leal-Witt, María Jesús and Acevedo, Alejandro and Muñoz, Manuel and Gudenschwager, Camila and Arias, Carolina and Cabello, Juan Francisco and La Marca, Giancarlo and Rizzo, Cristiano and Pietrobattista, Andrea and Spada, Marco and Dionisi-Vici, Carlo and Cornejo, Verónica},
  title = {Integrating Machine Learning and Follow-Up Variables to Improve Early Detection of Hepatocellular Carcinoma in Tyrosinemia Type 1: A Multicenter Study},
  journal = {International Journal of Molecular Sciences},
  year = {2025},
  doi = {10.3390/ijms26083839}
}
Kostenlos starten →