THE PANCREATIC Cancer Collective, which is the strategic partnership of the Lustgarten Foundation and Stand Up To Cancer (SU2C), recently announced that it has awarded $1 million grants to each of 2 projects that are using artificial intelligence (AI) computational approaches to identify high-risk pancreatic cancer populations. The grant money will be used to develop novel tools to identify individuals who are at high risk, based on their health records.
The two teams will each pursue a different approach to identifying high-risk individuals. One will use molecular and genetic data taken from a variety of data sets to identify new and accessible ways to identify high-risk individuals. The other team will focus on the identification of high-risk individuals by applying machine-learning analysis to real-world data comprising radiologic images, electronic medical records, and information collected by physicians. Each team will receive up to $1 million over 2 years.
Genomic and Immune Factors
THE TEAM leader for the first team is Raul Rabadan, PhD, of Columbia University, and the co-leader is Núria Malats, MD, PhD, MPH, of the Spanish National Cancer Research Centre. This team will focus on rare gene variants, specific DNA regions, and modifications, within large clinical and molecular data sets from multiple cohorts. The data sets include the UK Biobank, the European Study on Digestive Illnesses and Genetics, The Cancer Genome Atlas, and the International Cancer Genome Consortium. This team also plans to characterize the tumor microenvironment, specifically the microbiome and expression of proteins important for immune system regulation.
Machine-Learning Analysis of Clinical Records and Images
THE TEAM leader of this second team is Chris Sander, PhD, of Dana-Farber Cancer Institute, and the co-leader is Regina Barzilay, PhD, of Massachusetts Institute of Technology. The goal of this team’s project is to develop risk assessment models by using machine-learning analysis of clinical records and images to identify high-risk individuals for pancreatic cancer in the general population. These risk models will lead to a practical tool that can identify patients who are at elevated risk for pancreatic cancer and should be enrolled in screening programs for disease prevention and early detection. ■
