{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,11]],"date-time":"2026-11-11T00:08:21Z","timestamp":1794355701006,"version":"4.9.0"},"reference-count":39,"publisher":"BMJ","license":[{"start":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T00:00:00Z","timestamp":1777334400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Champions for Hope Pancreatic Cancer Research Program of the Funk Zitiello Foundation"},{"name":"Hoveida Family Foundation"},{"name":"Mayo Clinic Comprehensive Cancer Center"},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA256969"],"award-info":[{"award-number":["R01CA256969"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA272628"],"award-info":[{"award-number":["R01CA272628"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Centene Charitable Foundation"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Gut"],"accepted":{"date-parts":[[2026,3,5]]},"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Failure of conventional imaging to detect pancreatic ductal adenocarcinoma (PDA) at its visually occult pre-diagnostic stage is a primary barrier to improving its otherwise poor rate of survival.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop and validate the Radiomics-based Early Detection MODel (REDMOD), an AI framework to identify subvisual radiomic signatures of pre-diagnostic PDA on standard-of-care CT.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Designs<\/jats:title>\n                    <jats:p>REDMOD was trained on a multi-institutional cohort (n=969; 156 pre-diagnostic, 813 control) and tested on an independent set (n=493; 63 pre-diagnostic, 430 control), simulating a low prevalence (~1:6) early detection paradigm. The fully automated framework couples AI-driven segmentation with a heterogeneous ensemble architecture trained on a 40-feature radiomic signature derived from Synthetic Minority Over-sampling Technique (SMOTE)-balanced data. A tunable Youden Index-optimised classification threshold enables performance calibration without retraining. Validation included direct comparison with radiologists, longitudinal test\u2013retest analysis and external specificity validation across two independent cohorts (n=539\u2009and n=80).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On an independent test set (n=493), REDMOD identified occult PDA (AUC 0.82; 73.0% sensitivity) at a median 475-day lead time. This represented nearly twofold higher sensitivity than radiologists (38.9%; p&lt;0.001), which grew to nearly threefold (68.0% vs 23.0%) at &gt;24 months lead time. REDMOD showed strong longitudinal stability (90\u201392%\u2009concordance) and generalisable specificity across multi-institutional (81.3%; n=539) and public (87.5%; n=80) datasets. Mechanistic analyses confirmed predictive power derived principally from multi-scale wavelet-filtered textural features (90% of selected signature), which outperformed unfiltered features (AUC 0.82 vs 0.74; p=0.007) in capturing subvisual architectural disruptions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>REDMOD is an automated, mechanistically grounded, longitudinally stable, externally validated AI that surpasses radiologists for PDA detection at its visually occult pre-diagnostic stage. These attributes position it for prospective validation in high-risk cohorts, a necessary step towards shifting the paradigm from late-stage symptomatic diagnosis to proactive pre-clinical interception.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/gutjnl-2025-337266","type":"journal-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:11Z","timestamp":1777420811000},"page":"gutjnl-2025-337266","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":14,"title":["Next-generation AI for visually occult pancreatic cancer detection in a low-prevalence setting with longitudinal stability and multi-institutional generalisability"],"prefix":"10.1136","author":[{"given":"Sovanlal","family":"Mukherjee","sequence":"first","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ajith","family":"Antony","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Texas MD Anderson Cancer Center, Houston, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nandakumar G","family":"Patnam","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamaxi H","family":"Trivedi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aashna","family":"Karbhari","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"},{"name":"Radiology, University of Washington, Seattle, Washington, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khurram Khaliq","family":"Bhinder","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armin","family":"Zarrintan","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joel G","family":"Fletcher","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"Truty","sequence":"additional","affiliation":[{"name":"Surgery, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew P","family":"Johnson","sequence":"additional","affiliation":[{"name":"Quantitative Health Sciences, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3924-0971","authenticated-orcid":false,"given":"Suresh T","family":"Chari","sequence":"additional","affiliation":[{"name":"Gastroenterology, Hepatology and Nutrition, University of Texas MD Anderson Cancer Center, Houston, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7804-2695","authenticated-orcid":false,"given":"Ajit Harishkumar","family":"Goenka","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"2026042817000558000_gutjnl-2025-337266v1.1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21871"},{"key":"2026042817000558000_gutjnl-2025-337266v1.2","doi-asserted-by":"publisher","DOI":"10.1097\/MPA.0000000000001762"},{"key":"2026042817000558000_gutjnl-2025-337266v1.3","doi-asserted-by":"publisher","DOI":"10.1097\/MPA.0000000000000368"},{"key":"2026042817000558000_gutjnl-2025-337266v1.4","first-page":"1","article-title":"Artificial Intelligence-Augmented Imaging for Early Pancreatic Cancer Detection","volume":"2025","author":"Antony","year":"2025","journal-title":"Visc Med"},{"key":"2026042817000558000_gutjnl-2025-337266v1.5","doi-asserted-by":"publisher","DOI":"10.1016\/j.gastro.2005.05.007"},{"key":"2026042817000558000_gutjnl-2025-337266v1.6","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2018.05.023"},{"key":"2026042817000558000_gutjnl-2025-337266v1.7","unstructured":"National Institute for Health and Care Excellence (NICE) . Suspected cancer: recognition and referral. NICE Guideline NG12. 2025. Available: https:\/\/www.nice.org.uk\/guidance\/ng12\/chapter\/Recommendations-organised-by-site-of-cancer [Accessed 26 Sep 2025]."},{"key":"2026042817000558000_gutjnl-2025-337266v1.8","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.1007\/s00261-024-04775-x","article-title":"AI-driven insights in pancreatic cancer imaging: from pre-diagnostic detection to prognostication","volume":"50","author":"Antony","year":"2025","journal-title":"Abdom Radiol (NY)"},{"key":"2026042817000558000_gutjnl-2025-337266v1.9","doi-asserted-by":"crossref","first-page":"1435","DOI":"10.1053\/j.gastro.2022.06.066","article-title":"Radiomics-based Machine-learning Models Can Detect Pancreatic Cancer on Prediagnostic Computed Tomography Scans at a Substantial Lead Time Before Clinical Diagnosis","volume":"163","author":"Mukherjee","year":"2022","journal-title":"Gastroenterology"},{"key":"2026042817000558000_gutjnl-2025-337266v1.10","doi-asserted-by":"crossref","first-page":"964","DOI":"10.1007\/s00261-023-04127-1","article-title":"Assessing the robustness of a machine-learning model for early detection of pancreatic adenocarcinoma (PDA): evaluating resilience to variations in image acquisition and radiomics workflow using image perturbation methods","volume":"49","author":"Mukherjee","year":"2024","journal-title":"Abdom Radiol (NY)"},{"key":"2026042817000558000_gutjnl-2025-337266v1.11","doi-asserted-by":"crossref","first-page":"211","DOI":"10.3233\/CBM-210273","article-title":"Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images","volume":"33","author":"Qureshi","year":"2022","journal-title":"Cancer Biomark"},{"key":"2026042817000558000_gutjnl-2025-337266v1.12","doi-asserted-by":"crossref","DOI":"10.3389\/fonc.2022.1007990","article-title":"Risk prediction of pancreatic cancer using AI analysis of pancreatic subregions in computed tomography images","volume":"12","author":"Javed","year":"2022","journal-title":"Front Oncol"},{"key":"2026042817000558000_gutjnl-2025-337266v1.13","doi-asserted-by":"crossref","DOI":"10.14309\/ctg.0000000000000548","article-title":"Quantitative Radiomic Features From Computed Tomography Can Predict Pancreatic Cancer up to 36 Months Before Diagnosis","volume":"14","author":"Chen","year":"2023","journal-title":"Clin Transl Gastroenterol"},{"key":"2026042817000558000_gutjnl-2025-337266v1.14","doi-asserted-by":"crossref","first-page":"841","DOI":"10.1097\/RCT.0000000000001374","article-title":"Volumetric Pancreas Segmentation on Computed Tomography: Accuracy and Efficiency of a Convolutional Neural Network Versus Manual Segmentation in 3D Slicer in the Context of Interreader Variability of Expert Radiologists","volume":"46","author":"Khasawneh","year":"2022","journal-title":"J Comput Assist Tomogr"},{"key":"2026042817000558000_gutjnl-2025-337266v1.15","doi-asserted-by":"crossref","first-page":"2468","DOI":"10.1002\/mp.14782","article-title":"Two-stage deep learning model for fully automated pancreas segmentation on computed tomography: Comparison with intra-reader and inter-reader reliability at full and reduced radiation dose on an external dataset","volume":"48","author":"Panda","year":"2021","journal-title":"Med Phys"},{"key":"2026042817000558000_gutjnl-2025-337266v1.16","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2023.08.034"},{"key":"2026042817000558000_gutjnl-2025-337266v1.17","doi-asserted-by":"crossref","DOI":"10.2214\/AJR.24.31151","article-title":"Imaging for Early Detection of Pancreatic Ductal Adenocarcinoma: Updates and Challenges in the Implementation of Screening and Surveillance Programs","volume":"223","author":"Huang","year":"2024","journal-title":"AJR Am J Roentgenol"},{"key":"2026042817000558000_gutjnl-2025-337266v1.18","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-025-01802-9","article-title":"Pancreas segmentation using AI developed on the largest CT dataset with multi-institutional validation and implications for early cancer detection","volume":"15","author":"Mukherjee","year":"2025","journal-title":"Sci Rep"},{"key":"2026042817000558000_gutjnl-2025-337266v1.19","doi-asserted-by":"crossref","DOI":"10.3389\/fneur.2024.1305543","article-title":"Synthetic minority over-sampling technique-enhanced machine learning models for predicting recurrence of postoperative chronic subdural hematoma","volume":"15","author":"Ni","year":"2024","journal-title":"Front Neurol"},{"key":"2026042817000558000_gutjnl-2025-337266v1.20","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"2026042817000558000_gutjnl-2025-337266v1.21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2005.159"},{"key":"2026042817000558000_gutjnl-2025-337266v1.22","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1016\/j.pan.2021.03.016","article-title":"Quality gaps in public pancreas imaging datasets: Implications & challenges for AI applications","volume":"21","author":"Suman","year":"2021","journal-title":"Pancreatology"},{"key":"2026042817000558000_gutjnl-2025-337266v1.23","doi-asserted-by":"crossref","first-page":"1150","DOI":"10.1158\/1055-9965.EPI-23-1594","article-title":"Designing Rigorous and Efficient Clinical Utility Studies for Early Detection Biomarkers","volume":"33","author":"Zheng","year":"2024","journal-title":"Cancer Epidemiol Biomarkers Prev"},{"key":"2026042817000558000_gutjnl-2025-337266v1.24","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2021.10.014"},{"key":"2026042817000558000_gutjnl-2025-337266v1.25","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1053\/j.gastro.2021.11.021","article-title":"Late-Stage Pancreatic Cancer Detected During High-Risk Individual Surveillance: A Systematic Review and Meta-Analysis","volume":"162","author":"Chhoda","year":"2022","journal-title":"Gastroenterology"},{"key":"2026042817000558000_gutjnl-2025-337266v1.26","doi-asserted-by":"publisher","DOI":"10.1136\/gutjnl-2014-308653"},{"key":"2026042817000558000_gutjnl-2025-337266v1.27","doi-asserted-by":"publisher","DOI":"10.1097\/00000658-199603000-00007"},{"key":"2026042817000558000_gutjnl-2025-337266v1.28","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2019.01.259"},{"key":"2026042817000558000_gutjnl-2025-337266v1.29","unstructured":"PYMNTS . Mayo Clinic Uses AI to Detect Pancreatic Cancer Earlier. 2025. Available: https:\/\/www.pymnts.com\/artificial-intelligence-2\/2025\/mayo-clinic-uses-ai-to-detect-pancreatic-cancer-earlier\/ [Accessed 17 Dec 2025]."},{"key":"2026042817000558000_gutjnl-2025-337266v1.30","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1911793"},{"key":"2026042817000558000_gutjnl-2025-337266v1.31","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1600249"},{"key":"2026042817000558000_gutjnl-2025-337266v1.32","doi-asserted-by":"publisher","DOI":"10.1136\/thoraxjnl-2018-212152"},{"key":"2026042817000558000_gutjnl-2025-337266v1.33","article-title":"Does the availability of prior mammograms improve radiologists\u2019 observer performance? A scoping review","volume":"5","author":"Akwo","year":"2023","journal-title":"BJR Open"},{"key":"2026042817000558000_gutjnl-2025-337266v1.34","article-title":"Stromal Content Is Correlated With Tissue Site, Contrast Retention, and Survival in Pancreatic Adenocarcinoma","volume":"2018","author":"Torphy","year":"2018","journal-title":"JCO Precis Oncol"},{"key":"2026042817000558000_gutjnl-2025-337266v1.35","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-20-0841"},{"key":"2026042817000558000_gutjnl-2025-337266v1.36","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1053\/j.gastro.2025.06.025","article-title":"Risk of Pancreatic Cancer in Glycemically Defined New-Onset Diabetes: A Prospective Cohort Study","volume":"170","author":"Chari","year":"2026","journal-title":"Gastroenterology"},{"key":"2026042817000558000_gutjnl-2025-337266v1.37","unstructured":"NIH RePORT . Anticancer ELNP nanovaccines for curative treatment of pancreatic cancer. 2025. Available: https:\/\/reporter.nih.gov\/search\/Oz5oAFm3kUqjvhzx1Kz7gQ\/project-details\/11040015#details [Accessed 26 Sep 2025]."},{"key":"2026042817000558000_gutjnl-2025-337266v1.38","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2024.8755","article-title":"Hepatocellular Carcinoma Screening in a Contemporary Cohort of At-Risk Patients","volume":"7","author":"Daher","year":"2024","journal-title":"JAMA Netw Open"},{"key":"2026042817000558000_gutjnl-2025-337266v1.39","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1002\/hep.32284","article-title":"Overdiagnosis of hepatocellular carcinoma: Prevented by guidelines?","volume":"75","author":"Rich","year":"2022","journal-title":"Hepatology"}],"container-title":["Gut"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/gutjnl-2025-337266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:15Z","timestamp":1777420815000},"score":1,"resource":{"primary":{"URL":"https:\/\/gut.bmj.com\/lookup\/doi\/10.1136\/gutjnl-2025-337266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,28]]},"references-count":39,"alternative-id":["10.1136\/gutjnl-2025-337266"],"URL":"https:\/\/doi.org\/10.1136\/gutjnl-2025-337266","relation":{},"ISSN":["0017-5749","1468-3288"],"issn-type":[{"value":"0017-5749","type":"print"},{"value":"1468-3288","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,28]]}}}