Summary
Specific challenges (biology, limited data, standards, compatibility, legal, quality, AI chasm, incentives) are identified, with mitigation strategies summarized and next steps identified.
Original Article
Early Detection of Pancreatic Cancer. Applying Artificial Intelligence to Electronic Health Records
Pancreas
Kenner, Barbara J. PhD; Abrams, Natalie D. PhD; Chari, Suresh T. MD; Field, Bruce F. MS; Goldberg, Ann E. BA; Hoos, William A. MBA; Klimstra, David S. MD; Rothschild, Laura J. MBA; Srivastava, Sudhir PhD, MPH, MS; Young, Matthew R. PhD; Go, Vay Liang W. MD
Abstract
The potential of artificial intelligence (AI) applied to clinical data from electronic health records (EHRs) to improve early detection for pancreatic and other cancers remains underexplored. The Kenner Family Research Fund, in collaboration with the Cancer Biomarker Research Group at the National Cancer Institute, organized the workshop entitled: “Early Detection of Pancreatic Cancer: Opportunities and Challenges in Utilizing Electronic Health Records (EHR)” in March 2021. The workshop included a select group of panelists with expertise in pancreatic cancer, EHR data mining, and AI-based modeling. This review article reflects the findings from the workshop and assesses the feasibility of AI-based data extraction and modeling applied to EHRs. It highlights the increasing role of data sharing networks and common data models in improving the secondary use of EHR data. Current efforts using EHR data for AI-based modeling to enhance early detection of pancreatic cancer show promise. Specific challenges (biology, limited data, standards, compatibility, legal, quality, AI chasm, incentives) are identified, with mitigation strategies summarized and next steps identified.
Acknowledgements
Presenters for the “Early Detection of Pancreatic Cancer: Opportunities and Challenges in Utilizing Electronic Health Records (EHR)” were David S. Klimstra, MD, of Memorial Sloan Kettering Cancer Center (MSKCC); Sudhir Srivastava, PhD, MPH, MS, of the NCI Cancer Biomarkers Research Group, Division of Cancer Prevention; Alex Milinovich, BS, of Lerner Research Institute at Cleveland Clinic; Shawn Murphy, MD, PhD, of Mass General Brigham; Michael Rosenthal, MD, PhD, of Dana-Farber Cancer Institute; Jason Perry Block, MD, MPH, of Harvard Medical School; Jennifer St. Sauver, MPH, PhD, Mayo Clinic; Pete Stetson, MD, MA, of Memorial Sloan Kettering Cancer Center; Limor Appelbaum, MD, Beth Israel Deaconess Medical Center; Matvey Palchuk, MD, MS, FAMIA, TriNetX, LLC; and Suresh Chari, MD, of The University of Texas MD Anderson Cancer Center. Workshop was moderated by William Hoos, Canopy Cancer Collective. Workshop Planning Committee Members were Sudhir Srivastava, PhD, MPH, MS; Natalie Abrams, PhD, and Matthew Young, PhD (National Cancer Institute); Vay Liang Go, MD; Suresh Chari, MD; David Klimstra, MD; Bruce Field; and William Hoos, MBA (Kenner Family Research Fund scientific board members); Laura Rothschild, MBA; Ann Goldberg, BA; and Barbara Kenner, PhD (Kenner Family Research Fund board members). Editing assistance was provided by Tara Coffin, PhD.