AI–Derived Electronic Tumor Marker For Cancer Antigen 19-9 Nonproducers With Pancreatic Ductal Adenocarcinoma

Can machine-learning techniques using available patient data provide valuable information on treatment response and prognosis among patients with pancreatic ductal adenocarcinoma (PDAC) who do not produce cancer antigen 19-9 (CA19-9)?In this cohort study, a machine-learning–derived electronic tumor marker (e19-9) was trained to predict the expected CA19-9 level among patients with PDAC and elevated CA19-9 levels. The e19-9 model was retrospectively applied to a cohort of 121 patients without elevated CA19-9 who received neoadjuvant treatment for PDAC and trends in e19-9 were informative of completion of treatment, metastatic progression, and overall survival.These results demonstrate that e19-9 is a noninvasive artificial intelligence–derived marker that has the potential to support clinical decisions.

Corresponding Author: Anai N. Kothari, MD, MS, Department of Surgery, Division of Surgical Oncology, Medical College of Wisconsin, 8701 Watertown Plank Rd, Milwaukee, WI 53226 (akothari@mcw.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.