Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Nov 6;80(12):glaf207.
doi: 10.1093/gerona/glaf207.

Advancing delirium detection through the Open Health Natural Language Processing Consortium and the Evolve to Next-Gen Accrual to Clinical Trials Network

Sunyang Fu  1 , Min Ji Kwak  2 , Jaerong Ahn  1 , Zhiyi Yue  3 , Shreyas Ranganath  2 , Joseph R Applegate  1 , Andrew Wen  1 , Liwei Wang  1 , Chenyu Li  4 , Michele Morris  4 , Kelly M Toth  5 , Timothy D Girard  5 , John D Osborne  6 , Richard E Kennedy  7 , Nelly-Estefanie Garduno-Rapp  8 , Phillip Reeder  8 , Justin F Rousseau  8   9 , Chao Yan  10 , You Chen  10   11 , Mayur B Patel  12 , Tyler J Murphy  12 , Bradley A Malin  10   11 , Chan Mi Park  13 , Heling Jia  14 , Sandeep Pagali  15 , Allyson K Palmer  15 , Jennifer St Sauver  16 , Sunghwan Sohn  14 , Elmer V Bernstam  1   2 , Shyam Visweswaran  17 , Yanshan Wang  4   17 , Hongfang Liu  1
Affiliations

Advancing delirium detection through the Open Health Natural Language Processing Consortium and the Evolve to Next-Gen Accrual to Clinical Trials Network

Sunyang Fu et al. J Gerontol A Biol Sci Med Sci. .

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: Artificial Intelligence; Delirium; Electronic Health Records; Natural Language Processing; Translational AI.

PubMed Disclaimer

Conflict of interest statement

S.F. received consulting fee from Tufts Medical Center. M.J.K. received consulting fee from Novo Nordisk and Endocrine and Diabetes Plus Clinic of Houston and received research funding from Medical AI, NIA, and UTHealth. T.D.G. receives research funding from the NIH, DOD, and Ceribell; served as an expert witness for Clark, May, Price, Lawley, Duncan & Paul, LLC; and served previously on an advisory board for Lungpacer Medical Inc. K.M.T. receives payment from Leventhal Puga Braley P.C. for expert witness services on nursing standards of practice. T.D.G. receives research funding from the NIH, DOD, and Ceribell; served as an expert witness for Clark, May, Price, Lawley, Duncan & Paul, LLC; and served previously on an advisory board for Lungpacer Medical Inc. M.B.P. receives research funding from the NIH, DOD, serves on Scientific Advisory Board of Liberate Medical and Associate Editor for Sabiston Textbook of Surgery. J.S. receives grant support from Moderna and NIH for unrelated studies.

References

    1. Inouye SK, Westendorp RG, Saczynski JS. Delirium in elderly people. Lancet. 2014;383:911-922. - PMC - PubMed
    1. Inouye SK, van Dyck CH, Alessi CA, Balkin S, Siegal AP, Horwitz RI. Clarifying confusion: the confusion assessment method. A new method for detection of delirium. Ann Intern Med. 1990;113:941-948. 10.7326/0003-4819-113-12-941 - DOI - PubMed
    1. Marcantonio ER. Delirium in hospitalized older adults. N Engl J Med. 2017;377:1456-1466. 10.1056/NEJMcp1605501 - DOI - PMC - PubMed
    1. Quispel-Aggenbach DWP, Schep-de Ruiter EPR, van Bergen W, Bolling JR, Zuidema SU, Luijendijk HJ. Prevalence and risk factors of delirium in psychogeriatric outpatients. Int J Geriatr Psychiatry. 2021;36:190-196. 10.1002/gps.5413 - DOI - PMC - PubMed
    1. Ryan DJ, O’Regan NA, Caoimh RO, et al. Delirium in an adult acute hospital population: predictors, prevalence and detection. BMJ Open. 2013;3:e001772. 10.1136/bmjopen-2012-001772 - DOI - PMC - PubMed