Peer-Reviewed Publication
JAMIA Open2026;9(5):ooag195.October 1, 2026Journal Article
Longitudinal symptom severity tracking in vagus nerve stimulation patients: a 2-stage LLM-based pipeline with explainable AI.
Vedansh Thakkar1,2, Greg M Silverman1,2, Maura Putzer1, Abhinab Kc3, Sana Ikramuddin3, Tanya Melnik1,2, Nicholas E Ingraham4,5, Nathan Keller3, Samantha King6, Emma Jones1, Angela Bailey3, Genevieve B Melton1,2,5, Christopher Tignanelli1,2,5
1Department of Surgery, University of Minnesota, Minneapolis, MN 55455, United States.
2Natural Language Processing/Information Extraction Program, University of Minnesota, Minneapolis, MN 55455, United States.
3University of Minnesota Medical School, Minneapolis, MN 55455, United States.
4Department of Pulmonary, Allergy, Critical Care, and Sleep Medicine, University of Minnesota, Minneapolis, MN 55455, United States.
5Center for Learning Health Systems Sciences, University of Minnesota, Minneapolis, MN 55455, United States.
6Department of Surgery, University of Washington, Seattle, WA 98195, United States.
Abstract
OBJECTIVES: To produce the first structured longitudinal dataset of symptom severity trajectories in vagus nerve stimulation (VNS) patients using a 2-stage large language model pipeline for automated symptom severity extraction from clinical notes, as part of the NIH-funded research evaluating vagal excitations and anatomical linkages (U54AT012307).
MATERIALS AND METHODS: We analyzed 1427 annotat…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans