Accessibility settings

Published on in Vol 28 (2026)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/91449, first published .
Hands sorting through stacks of documents with colorful sticky notes

Natural Language Processing Supported by Annotation Process Artifacts to Detect Risky Alcohol Use in Electronic Health Records: Algorithm Development and Validation Study

Natural Language Processing Supported by Annotation Process Artifacts to Detect Risky Alcohol Use in Electronic Health Records: Algorithm Development and Validation Study

Katherine Weber   1 , PhD ;   Asher Strayhorn   1 , BS ;   Xintong Ju   2 , MS ;   Jessica Mellinger   3 , MD, MSc ;   Gerald Scott Winder   4 , MD, MSc ;   Anne C Fernandez   2 * , PhD ;   VG Vinod Vydiswaran   1, 5 * , PhD

1 Department of Learning Health Sciences, Medical School, University of Michigan, Ann Arbor, MI, United States

2 Department of Psychiatry, Medical School, University of Michigan, Ann Arbor, MI, United States

3 Division of Gastroenterology & Hepatology, Department of Internal Medicine, Henry Ford Hospital, Detroit, MI, United States

4 Department of Psychiatry, Henry Ford Hospital, Detroit, MI, United States

5 School of Information, University of Michigan, Ann Arbor, MI, United States

*these authors contributed equally

Corresponding Author:

  • VG Vinod Vydiswaran, PhD
  • Department of Learning Health Sciences
  • Medical School
  • University of Michigan
  • 1111 E. Catherine Street
  • Room 209
  • Ann Arbor, MI 48109-2054
  • United States
  • Phone: 1 734 647 1207
  • Fax: 1 734 647 3914
  • Email: vgvinodv@umich.edu