Lung Cancer Detection Using Bayesian Networks: A Retrospective Development and Validation Study on a Danish Population of High‐Risk Individuals
Cancer Medicine · 2025
DOI: 10.1002/cam4.70458 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Cancer Medicine, 2025. Verfasst von Margrethe Bang Henriksen und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Oncology, Vejle University Hospital, Vejle, Denmark. Hauptthemen laut MEDLINE: Lung Neoplasms, Early Detection of Cancer. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Danish National Research Center for Lung Cancer, Danish Cancer Society, Beckett-Fonden, Syddansk Universitet.
Abstract (Originalsprache)
Background
Lung cancer (LC) is the top cause of cancer deaths globally, prompting many countries to adopt LC screening programs. While screening typically relies on age and smoking intensity, more efficient risk models exist. We devised a Bayesian network (BN) for LC detection, testing its resilience with varying degrees of missing data and comparing it to a prior machine learning (ML) model.
Methods
We analyzed data from 9940 patients referred for LC assessment in Southern Denmark from 2009 to 2018. Variables included age, sex, smoking, and lab results. Our experiments varied missing data (0%–30%), BN structure (expert‐based vs. data‐driven), and discretization method (standard vs. data‐driven).
Results
Across all missing data levels, area under the curve (AUC) remained steady, ranging from 0.737 to 0.757, compared to the ML model's AUC of 0.77. BN structure and discretization method had minimal impact on performance. BNs were well calibrated overall, with a net benefit in decision curve analysis when predicted risk exceeded 5%.
Conclusion
BN models showed resilience with up to 30% missing values. Moreover, these BNs exhibited similar performance, calibration, and clinical utility compared to the machine learning model developed using the same dataset. Considering their effectiveness in handling missing data, BNs emerge as a relevant method for the development of future lung cancer detection models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Oncology, Vejle University Hospital, Vejle, Denmark.
- Institute of Regional Health Research, University of Southern Denmark, Odense, Denmark.
- Department of Radiation Oncology (MAASTRO) GROW School for Oncology and Reproduction, Maastricht University Medical Centre+, Maastricht, the Netherlands.
- Department of Biochemistry and Immunology, Vejle University Hospital, Vejle, Denmark.
- Department of Internal Medicine, Vejle University Hospital, Vejle, Denmark.
- Data Science Institute (DSI), Hasselt University, Hasselt, Belgium.
ORCID-Profile: Margrethe Bang Henriksen, Florian Van Daalen, Leonard Wee, Torben Frøstrup Hansen, Lars Henrik Jensen, Claus Lohman Brasen, Ole Hilberg, Inigo Bermejo
Förderung
- The Danish National Research Center for Lung Cancer, Danish Cancer Society
- Beckett-Fonden
- Syddansk Universitet
- Region Syddanmark
- Lilly and Herbert Hansens Foundation
- Dagmar Marshalls Fond
- Familien Hede Nielsens Fond
Zitieren
APA
Henriksen, M. B., Van Daalen, F., Wee, L., Hansen, T. F., Jensen, L. H., Brasen, C. L., Hilberg, O., & Bermejo, I. (2025). Lung Cancer Detection Using Bayesian Networks: A Retrospective Development and Validation Study on a Danish Population of High‐Risk Individuals. Cancer Medicine. https://doi.org/10.1002/cam4.70458
Vancouver
Henriksen MB, Van Daalen F, Wee L, Hansen TF, Jensen LH, Brasen CL, et al. Lung Cancer Detection Using Bayesian Networks: A Retrospective Development and Validation Study on a Danish Population of High‐Risk Individuals. Cancer Medicine. 2025. doi:10.1002/cam4.70458
BibTeX
@article{Henriksen2025,
author = {Henriksen, Margrethe Bang and Van Daalen, Florian and Wee, Leonard and Hansen, Torben Frøstrup and Jensen, Lars Henrik and Brasen, Claus Lohman and Hilberg, Ole and Bermejo, Inigo},
title = {Lung Cancer Detection Using Bayesian Networks: A Retrospective Development and Validation Study on a Danish Population of High‐Risk Individuals},
journal = {Cancer Medicine},
year = {2025},
doi = {10.1002/cam4.70458}
}
EUVIMED