Paper Accepted: LLM-Based Case Identification for Eosinophilic Esophagitis

I’m excited to share that our manuscript on LLM-based case identification for eosinophilic esophagitis has been accepted for publication in Gastro Hep Advances.

Publication

Title: Development and Validation of a Large Language Model Case Identification Strategy for Eosinophilic Esophagitis

Authors:
Corey J Ketchem, Ugurcan Vurgun, Agnes Wang, Sunil Thomas, Ashley Batugo, John E Pandolfino,
Gary W Falk, Kristle L Lynch, Evan S Dellon, Danielle L Mowery, James D Lewis

Journal: Gastro Hep Advances (in press)

Summary

In this work, we developed and validated a large language model–based approach for identifying eosinophilic esophagitis cases from clinical data. This research shows the potential of LLMs to support more scalable and accurate case identification in gastroenterology.

Why it matters

This paper contributes to ongoing efforts to apply NLP and large language models to clinically meaningful problems, with relevance for disease surveillance, research cohort development, and future translational applications in medicine.

In-press citation

Ketchem CJ, Vurgun U, Wang A, Thomas S, Batugo A, Pandolfino JE, Falk GW, Lynch KL, Dellon ES, Mowery DL, Lewis JD. Development and Validation of a Large Language Model Case Identification Strategy for Eosinophilic Esophagitis. Gastro Hep Advances. In press.