# Predicting Pancreatic Ductal Adenocarcinoma PDAC Through Artificial Intelligence Analysis of Pre Diagnostic CT Images in African Americans > **NIH NIH R01** · CEDARS-SINAI MEDICAL CENTER · 2024 · $224,726 ## Abstract The objective of this administrative supplemental proposal is to demonstrate that a specific model is needed to improve the accuracy of predicting Pancreatic Ductal Adenocarcinoma (PDAC) risk in African Americans through Artificial Intelligence (AI) analysis of pre-diagnostic CT images. PDAC is the fourth leading cause of cancer-related deaths in both men and women in the United States despite its low incidence rate. PDAC has a high mortality rate in part because more than 80% of the patients are at advanced stages when they were diagnosed for the first time. Notably, there are significant racial disparities in PDAC incidence and mortality rates, with the highest rates in African Americans compared to Non-Hispanic Whites and Hispanics. The objective of the parent award is to develop a PDAC prediction model to identify individuals who have high risk for PDAC in the next 10 years through AI analysis of pre-diagnostic CT images. Identification of individuals at high risk for PDAC has high clinical significance as follow-up imaging examinations or biopsy may assist in early detection and allow surgical intervention while the tumors are still resectable. Pre-diagnostic CT images provide critical morphological information associated with underlying biological changes and heterogeneity at the pre-cancer or early cancer stage. A pilot study using data from the parent award identified a number of different radiomic features in pre-diagnostic CT scans that are predictive of future PDAC between African Americans and Whites. Based on these studies, we hypothesize that: i) pre- diagnostic CT image features associated with future PDAC occurrence are significantly different between African Americans and Whites; ii) CT radiomic model developed for the general population in the parent award is less accurate in African Americans than in the general population for PDAC prediction. To verify these hypotheses, we will retrospectively evaluate CT pancreatic images obtained up to 10 years prior to PDAC diagnosis that were deemed non-cancerous by radiologists. A group of subjects who underwent similar imaging studies for non-gastrointestinal disorders and were age/gender matched with pre-diagnostic imaging will serve as healthy controls. Pre-diagnostic CT radiomic features will be compared between African Americans and Whites. If they are significantly different, we will demonstrate that the CT radiomic model developed for the general population in the parent award is less accurate in African Americans than in the general population for PDAC prediction. The purpose of this administrative supplemental proposal pilot study is to demonstrate that there is need for a specific PDAC prediction model through AI analysis of pre-diagnostic CT images for African Americans to improve the PDAC prediction accuracy. Accurate prediction of PDAC has high clinical impact as it may allow early detection and treatment of this fatal disease, which has the highest rates of incidence and mor... ## Key facts - **NIH application ID:** 11014899 - **Project number:** 3R01CA260955-04S1 - **Recipient organization:** CEDARS-SINAI MEDICAL CENTER - **Principal Investigator:** Debiao Li - **Activity code:** R01 (R01, R21, SBIR, etc.) - **Funding institute:** NIH - **Fiscal year:** 2024 - **Award amount:** $224,726 - **Award type:** 3 - **Project period:** 2021-09-01 → 2026-08-31 ## Primary source NIH RePORTER: https://reporter.nih.gov/project-details/11014899 ## Citation > US National Institutes of Health, RePORTER application 11014899, Predicting Pancreatic Ductal Adenocarcinoma PDAC Through Artificial Intelligence Analysis of Pre Diagnostic CT Images in African Americans (3R01CA260955-04S1). Retrieved via AI Analytics 2026-05-28 from https://api.ai-analytics.org/grant/nih/11014899. Licensed CC0. --- *[NIH grants dataset](/datasets/nih-grants) · CC0 1.0*