EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

WDCN: a comprehensive neural network based approach for estimating breast cancer risk

Hanshi Xu, Guangquan Zhang, Hua Lin, Mark Grosser, Jie Lu iD

Briefings in Bioinformatics · 03.07.2026 · 27 (4)

DOI: 10.1093/bib/bbag412 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 06.08.2026. Verfasst von Hanshi Xu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Australian AI institute, Faculty of Engineering and Information Technology, University of Technology Sydney, 61 Broadway, Sydney 2007, New South Wale…. Hauptthemen laut MEDLINE: Breast Neoplasms, Neural Networks, Computer, Deep Learning. Die Arbeit nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Australian Research Council Linkage Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Breast cancer is one of the most distressing cancers affecting women, and early detection is considered the most effective way to reduce breast cancer mortality. However, the benefits of early detection vary among different risk groups. Therefore, using a combination of genetic information, family history, and other factors to stratify populations by risk can help more people benefit from early detection. Traditional polygenic risk score (PRS) is essentially a weighted sum calculation method that has achieved some success, but it neglects the interactions between genes–genes, genes–environment, and their potential impact on breast cancer risk. In this context, we developed a new deep learning-based method called wide, deep, and cross network (WDCN). Experimental results show that our algorithm outperforms PRS and other machine learning baseline methods and achieves an area under the receiver operating characteristic curve (AUROC) of 0.6439 when using 286 single nucleotide polymorphism (SNP) features and 0.8865 when incorporating environmental features with genetic data. Increasing the SNP set to 317 further raised the performance to 0.6464 and 0.8872, both with and without non-genetic factors. Risk stratification shows that individuals in the top 30% have a relative risk of 7.85 (95% CI: 6.98–8.83) compared with those in the bottom 30%. We also identified an interaction between rs2588809 and age. This novel approach has shown promise for initial risk stratification of populations, potentially providing better decision-making support for individuals and clinicians.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Breast NeoplasmsNeural Networks, ComputerDeep LearningHumansFemalePolymorphism, Single NucleotideGenetic Risk ScoreGenetic Predisposition to DiseaseAlgorithmsROC Curve

Stichwörter der Autor:innen

artificial neural networkbioinformatics approachbreast cancer

Autor:innen und Institutionen

  • Australian AI institute, Faculty of Engineering and Information Technology, University of Technology Sydney, 61 Broadway, Sydney 2007, New South Wales, Australia.
  • 23Strands, 26-32 Pirrama Road, Pyrmont 2009, New South Wales, Australia.

ORCID-Profile: Jie Lu

Förderung

  • Australian Research Council Linkage Project

Zitieren

APA

Xu, H., Zhang, G., Lin, H., Grosser, M., & Lu, J. (2026). WDCN: a comprehensive neural network based approach for estimating breast cancer risk. Briefings in Bioinformatics, 27(4). https://doi.org/10.1093/bib/bbag412

Vancouver

Xu H, Zhang G, Lin H, Grosser M, Lu J. WDCN: a comprehensive neural network based approach for estimating breast cancer risk. Briefings in Bioinformatics. 2026;27(4). doi:10.1093/bib/bbag412

BibTeX
@article{Xu2026,
  author = {Xu, Hanshi and Zhang, Guangquan and Lin, Hua and Grosser, Mark and Lu, Jie},
  title = {WDCN: a comprehensive neural network based approach for estimating breast cancer risk},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {4},
  doi = {10.1093/bib/bbag412}
}
Kostenlos starten →