Explainable machine learning identifies a polygenic risk score as a key predictor of pancreatic cancer risk in the UK Biobank
Digestive and Liver Disease · 2025
DOI: 10.1016/j.dld.2024.11.010 ↗Kurz gefasst
Fachartikel in der Zeitschrift Digestive and Liver Disease, 2025. Verfasst von Giulia Peduzzi und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biology, University of Pisa, Via Luca Ghini, 13 - 56126, Pisa, Italy. Electronic address: giulia.peduzzi@biologia.unipi.it. Hauptthemen laut MEDLINE: Machine Learning, Pancreatic Neoplasms, Carcinoma, Pancreatic Ductal. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 55 Literaturangaben.
Abstract (Originalsprache)
BACKGROUND: Predicting the risk of developing pancreatic ductal adenocarcinoma (PDAC) is of paramount importance, given its high mortality rate. Current PDAC risk prediction models rely on a limited number of variables, do not include genetics, and have a modest accuracy. AIM: This study aimed to develop an interpretable PDAC risk prediction model, based on machine learning (ML). METHODS: Five ML models (Adaptive Boosting, eXtreme Gradient Boosting, CatBoost, Deep Forest and Random Forest) built on 56 exposome variables and a polygenic risk score (PRS) were tested in 654 PDAC cases and 1,308 controls of the UK Biobank. Additionally, SHapley Additive exPlanation (SHAP) and Global model Interpretation via the Recursive Partitioning (Girp) were employed to explain the models. RESULTS: All models provided similar performance, but based on recall the best was CatBoost (77.10 %). SHAP highlighted age and the PRS as primary contributors across all models. Girp developed rules to discern cases from controls, identifying age, PRS, and pancreatitis in most of the rules. CONCLUSION: The predictive models tested have exhibited good performance, indicating their potential application in the clinical field in the near future, with the PRS playing a key role in identifying high-risk individuals as demonstrated by the explainers.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Biology, University of Pisa, Via Luca Ghini, 13 - 56126, Pisa, Italy. Electronic address: giulia.peduzzi@biologia.unipi.it.
- Department of Biology, University of Pisa, Via Luca Ghini, 13 - 56126, Pisa, Italy. Electronic address: alessio.felici@phd.unipi.it.
- Classe di scienze, Scuola Normale Superiore, Piazza dei Cavalieri, 7 - 56126, Pisa, Italy. Electronic address: roberto.pellungrini@sns.it.
- Department of Biology, University of Pisa, Via Luca Ghini, 13 - 56126, Pisa, Italy. Electronic address: daniele.campa@unipi.it.
Zitieren
APA
Peduzzi, G., Felici, A., Pellungrini, R., & Campa, D. (2025). Explainable machine learning identifies a polygenic risk score as a key predictor of pancreatic cancer risk in the UK Biobank. Digestive and Liver Disease. https://doi.org/10.1016/j.dld.2024.11.010
Vancouver
Peduzzi G, Felici A, Pellungrini R, Campa D. Explainable machine learning identifies a polygenic risk score as a key predictor of pancreatic cancer risk in the UK Biobank. Digestive and Liver Disease. 2025. doi:10.1016/j.dld.2024.11.010
BibTeX
@article{Peduzzi2025,
author = {Peduzzi, Giulia and Felici, Alessio and Pellungrini, Roberto and Campa, Daniele},
title = {Explainable machine learning identifies a polygenic risk score as a key predictor of pancreatic cancer risk in the UK Biobank},
journal = {Digestive and Liver Disease},
year = {2025},
doi = {10.1016/j.dld.2024.11.010}
}
EUVIMED