Advancing Delirium Detection Through the Open Health Natural Language Processing Consortium and the Evolve to Next-Gen Accrual to Clinical Trials Network

Authors

• Sunyang Fu
• Min Ji Kwak
• Jaerong Ahn
• Zhiyi Yue
• Shreyas Ranganath
• Joseph R Applegate
• Andrew Wen
• Liwei Wang
• Chenyu Li
• Michele Morris
• Kelly M Toth
• Timothy D Girard
• John D Osborne
• Richard E Kennedy
• Nelly-Estefanie Garduno-Rapp
• Phillip Reeder
• Justin F Rousseau
• Chao Yan
• You Chen
• Mayur B Patel
• Tyler J Murphy
• Bradley A Malin
• Chan Mi Park
• Heling Jia
• Sandeep Pagali
• Allyson K Palmer
• Jennifer St Sauver
• Sunghwan Sohn
• Elmer V Bernstam
• Shyam Visweswaran
• Yanshan Wang
• Hongfang Liu

Language

English

Publication Date

11-6-2025

Journal

The Journals of Gerontology: Series A

DOI

10.1093/gerona/glaf207

PMID

41017643

PMCID

PMC12622219

PubMedCentral® Posted Date

7-11-2026

PubMedCentral® Full Text Version

Author MSS

Abstract

Background: Delirium is often underdiagnosed in clinical practice and is not routinely coded for billing. While manual chart review can identify delirium, it is labor-intensive and impractical for large-scale studies. Natural language processing (NLP) can analyze unstructured text in electronic health records (EHRs) to extract meaningful clinical information.

Methods: To support national integration of NLP for EHR-based delirium identification across different institutions, we launched the Delirium Interest Group within the national Evolve to Next-Gen Accrual to Clinical Trials (ENACT) NLP Working Group. This paper outlines our initial efforts to standardize, evaluate, and translate an NLP-based delirium detection model into the i2b2/ENACT platform.

Results: Multisite contextual inquiry identified several key challenges, including variations in local screening practices (eg, tools used, documentation frequency, and quality control), the need for harmonized definitions in the context of EHRs, and the complexity of modeling temporal logic. Multisite NLP evaluation revealed variable performance degradation driven by differences in delirium screening practices, clinical documentation patterns and semantics, and note syntactic structures.

Conclusion: Our work represents an important first step toward enabling scalable and standardized NLP-based delirium detection across institutions. By engaging diverse institutions through the ENACT NLP Working Group, we identified shared challenges and site-specific variations that impact model implementation and performance. Our collaborative approach enabled the development of a more robust framework for delirium identification across heterogeneous EHR systems. Future efforts will build on this foundation to enhance the validity, usability, and translational impact of delirium detection.

Keywords

Natural Language Processing, Humans, Delirium, Electronic Health Records, Clinical Trials as Topic, Artificial Intelligence, Delirium, Electronic Health Records, Natural Language Processing, Translational AI

Published Open-Access

yes

Recommended Citation

Fu, Sunyang; Kwak, Min Ji; Ahn, Jaerong; et al., "Advancing Delirium Detection Through the Open Health Natural Language Processing Consortium and the Evolve to Next-Gen Accrual to Clinical Trials Network" (2025). Faculty, Staff and Student Publications. 821.
https://digitalcommons.library.tmc.edu/uthshis_docs/821