A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories

Placido, Davide; Yuan, Bo; Hjaltelin, Jessica Xin; Zheng, Chunlei; Haue, Amalie Dahl; Chmura, Piotr Jaroslaw; Yuan, Chen; Kim, Jihye; Umeton, Renato; Antell, Gregory C.; Chowdhury, Alexander; Franz, Alexandra; Brais, Lauren K.; Andrews, Elizabeth; Marks, Debora S.; Regev, Aviv; Ayandeh, Siamack; Brophy, Mary T.; Do, Nhan; Kraft, Peter; Wolpin, Brian M.; Rosenthal, Michael H.; Fillmore, Nathanael R.; Brunak, Søren; Sander, Chris

doi:10.1038/s41591-023-02332-5

articleNature MedicineMay 1, 2023HYBRID OA

A deep learning algorithm to predict risk of pancreatic cancer from disease trajectories

DPDavide Placido BYBo Yuan JXJessica Xin Hjaltelin CZChunlei Zheng ADAmalie Dahl Haue

University of Copenhagen · Novo Nordisk Foundation · +10 more institutions

PubMed

Indexed incrossrefpubmed

Abstract

Pancreatic cancer is an aggressive disease that typically presents late with poor outcomes, indicating a pronounced need for early detection. In this study, we applied artificial intelligence methods to clinical data from 6 million patients (24,000 pancreatic cancer cases) in Denmark (Danish National Patient Registry (DNPR)) and from 3 million patients (3,900 cases) in the United States (US Veterans Affairs (US-VA)). We trained machine learning models on the sequence of disease codes in clinical histories and tested prediction of cancer occurrence within incremental time windows (CancerRiskNet). For cancer occurrence within 36 months, the performance of the best DNPR model has area under the receiver operating…

Citation impact

309

total citations

FWCI: 67.18
Percentile: 100%
References: 60

Citations per year

Authors

25

Topics & keywords

Topics

Keywords

Medicine
Receiver operating characteristic
Cancer
Pancreatic cancer
Disease
Cancer registry
Danish
Machine learning

No related works found for this paper.