Digitally enriching a high-risk population for pancreatic cancer using routine blood-based measures and clinical histories
Abstract
Earlier detection of pancreatic cancer is key to enabling wider access to curative treatment and reducing cancer deaths; however, screening is presently not viable. Latent digital indicators of pathology are evident in an individual's disease and blood test trajectories and may predict the development of pancreatic cancer. Longitudinal sequences of coded diagnoses and blood test values accrued by patients throughout their clinical interactions were used to train a custom Transformer-based neural network with a multi-head attention mechanism to predict risk of pancreatic cancer with a multi-year lead time and risk-stratify populations for targeted screening. Mayo Clinic Platform with trained model from Mayo Clinic Rochester validated at Mayo Clinic Arizona, Mayo Clinic Florida, and Mayo Clinic Health Systems. The cohort comprised 6,017 adults with pancreatic cancer and 177,081 controls (median age 75, 45% female) with median 12 years (interquartile range 6.9-16.2) of medical history prior to pancreatic cancer diagnosis. External validation via leave-one-site-out, out-of-sample testing predicting pancreatic cancer 1-, 2-, and 3-years prior to diagnosis demonstrated mean area under the receiver operating characteristic of 0.837 (95% confidence interval 0.827-0.848), 0.797 (95% confidence interval 0.782-0.813), and 0.760 (95% confidence interval 0.745-0.776), respectively. Estimated pancreatic cancer risks were well-calibrated (calibration plot slope 1.08, intercept of -0.077; Brier score 0.025), and a Bayesian population pancreatic cancer prevalence update allows estimated cancer risk outputs to be transportable across settings. At testing, a screening threshold of >3.3% risk of pancreatic cancer in 1-year offered a diagnostic odds ratio of 18.2. Our work therefore lays the foundation for a digital population-level risk enrichment tool that could widen access to curative-intent management.
Related
- Development and psychometric validation of Mpox knowledge and preventive behavior measures in the Turkish population
- 345 Neoantigen-targeted adoptive cell therapy in bladder cancer: feasibility of isolating and enriching tumor-reactive infiltrating lymphocytes
- Enriching microlaser-labelled cells by commercial flow cytometry-based cell sorting systems
- A Three-Domain Framework for Trust in Digitally Mediated Social Life
- SedaDNA metabarcoding reveals hidden histories of within-species sequence variation
BibTeX
@misc{varghese2026digitally,
title = {{Digitally enriching a high-risk population for pancreatic cancer using routine blood-based measures and clinical histories}},
author = {Chris Varghese and Leo Y. Li-Han and Richa Bisht and Ellen Larson and Frank Lee and Ryan M. Carr and Tanios S. Bekaii-Saab and Shounak Majumder and John D. Halamka and Mark Truty and Ajit H. Goenka and Hojjat Salehinejad and Cornelius A. Thiels},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.30275},
eprint = {2605.30275},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.30275},
note = {CC BY-NC-SA 4.0},
}
RIS
TY - UNPB
TI - Digitally enriching a high-risk population for pancreatic cancer using routine blood-based measures and clinical histories
AU - Chris Varghese
AU - Leo Y. Li-Han
AU - Richa Bisht
AU - Ellen Larson
AU - Frank Lee
AU - Ryan M. Carr
AU - Tanios S. Bekaii-Saab
AU - Shounak Majumder
AU - John D. Halamka
AU - Mark Truty
AU - Ajit H. Goenka
AU - Hojjat Salehinejad
AU - Cornelius A. Thiels
PY - 2026
DA - 2026/09/27
PB - arXiv
DO - 10.48550/arxiv.2605.30275
UR - https://arxiv.org/abs/2605.30275
AB - Earlier detection of pancreatic cancer is key to enabling wider access to curative treatment and reducing cancer deaths; however, screening is presently not viable. Latent digital indicators of pathology are evident in an individual's disease and blood test trajectories and may predict the development of pancreatic cancer. Longitudinal sequences of coded diagnoses and blood test values accrued by patients throughout their clinical interactions were used to train a custom Transformer-based neural network with a multi-head attention mechanism to predict risk of pancreatic cancer with a multi-year lead time and risk-stratify populations for targeted screening. Mayo Clinic Platform with trained model from Mayo Clinic Rochester validated at Mayo Clinic Arizona, Mayo Clinic Florida, and Mayo Clinic Health Systems. The cohort comprised 6,017 adults with pancreatic cancer and 177,081 controls (median age 75, 45% female) with median 12 years (interquartile range 6.9-16.2) of medical history prior to pancreatic cancer diagnosis. External validation via leave-one-site-out, out-of-sample testing predicting pancreatic cancer 1-, 2-, and 3-years prior to diagnosis demonstrated mean area under the receiver operating characteristic of 0.837 (95% confidence interval 0.827-0.848), 0.797 (95% confidence interval 0.782-0.813), and 0.760 (95% confidence interval 0.745-0.776), respectively. Estimated pancreatic cancer risks were well-calibrated (calibration plot slope 1.08, intercept of -0.077; Brier score 0.025), and a Bayesian population pancreatic cancer prevalence update allows estimated cancer risk outputs to be transportable across settings. At testing, a screening threshold of >3.3% risk of pancreatic cancer in 1-year offered a diagnostic odds ratio of 18.2. Our work therefore lays the foundation for a digital population-level risk enrichment tool that could widen access to curative-intent management.
ER -