Advancing delirium detection through the Open Health Natural Language Processing Consortium and the Evolve to Next-Gen Accrual to Clinical Trials Network.
Saved in:
| Title: | Advancing delirium detection through the Open Health Natural Language Processing Consortium and the Evolve to Next-Gen Accrual to Clinical Trials Network. |
|---|---|
| Authors: | Fu S; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States., Kwak MJ; McGovern Medical School, University of Texas Health Science Center at Houston, Houston, Texas, United States., Ahn J; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States., Yue Z; School of Public Health, University of Texas Health Science Center at Houston, Houston, Texas, United States., Ranganath S; McGovern Medical School, University of Texas Health Science Center at Houston, Houston, Texas, United States., Applegate JR; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States., Wen A; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States., Wang L; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States., Li C; Department of Health Information Management, University of Pittsburgh, Pittsburgh, Pennsylvania, United States., Morris M; Department of Health Information Management, University of Pittsburgh, Pittsburgh, Pennsylvania, United States., Toth KM; Center for Research, Investigation, and Systems Modeling of Acute Illness (CRISMA) in the Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States., Girard TD; Center for Research, Investigation, and Systems Modeling of Acute Illness (CRISMA) in the Department of Critical Care Medicine, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, United States., Osborne JD; Department of Biomedical Informatics and Data Science, University of Alabama at Birmingham, Birmingham, Alabama, United States., Kennedy RE; Department of Gerontology, Geriatrics, and Palliative Care, University of Alabama at Birmingham, Birmingham, Alabama, United States., Garduno-Rapp NE; Clinical Informatics Center, University of Texas Southwestern Medical Center, Dallas, Texas, United States., Reeder P; Clinical Informatics Center, University of Texas Southwestern Medical Center, Dallas, Texas, United States., Rousseau JF; Clinical Informatics Center, University of Texas Southwestern Medical Center, Dallas, Texas, United States.; Biostatistics and Clinical Informatics Division, Department of Neurology, University of Texas Southwestern Medical Center, Dallas, Texas, United States., Yan C; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States., Chen Y; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States.; Department of Computer Science, Vanderbilt University, Nashville, Tennessee, United States., Patel MB; Section of Surgical Sciences, Division of Acute Care Surgery, Department of Surgery, Vanderbilt University Medical Center, Nashville, Tennessee, United States., Murphy TJ; Section of Surgical Sciences, Division of Acute Care Surgery, Department of Surgery, Vanderbilt University Medical Center, Nashville, Tennessee, United States., Malin BA; Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States.; Department of Computer Science, Vanderbilt University, Nashville, Tennessee, United States., Park CM; Department of Gerontology, Hebrew SeniorLife, Marcus Institute for Aging Research, Boston, Massachusetts, United States., Jia H; Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, Minnesota, United States., Pagali S; Department of Medicine, Mayo Clinic, Rochester, Minnesota, United States., Palmer AK; Department of Medicine, Mayo Clinic, Rochester, Minnesota, United States., Sauver JS; Division of Epidemiology, Department of Quantitative Health Sciences, Mayo Clinic, Rochester, Minnesota, United States., Sohn S; Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, Minnesota, United States., Bernstam EV; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States.; McGovern Medical School, University of Texas Health Science Center at Houston, Houston, Texas, United States., Visweswaran S; Clinical and Translational Science Institute, University of Pittsburgh, Pittsburgh, Pennsylvania, United States., Wang Y; Department of Health Information Management, University of Pittsburgh, Pittsburgh, Pennsylvania, United States.; Clinical and Translational Science Institute, University of Pittsburgh, Pittsburgh, Pennsylvania, United States., Liu H; McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, Texas, United States. |
| Source: | The journals of gerontology. Series A, Biological sciences and medical sciences [J Gerontol A Biol Sci Med Sci] 2025 Nov 06; Vol. 80 (12). |
| Publication Type: | Journal Article |
| Language: | English |
| Journal Info: | Publisher: published on behalf of the Gerontological Society of America by Oxford University Press Country of Publication: United States NLM ID: 9502837 Publication Model: Print Cited Medium: Internet ISSN: 1758-535X (Electronic) Linking ISSN: 10795006 NLM ISO Abbreviation: J Gerontol A Biol Sci Med Sci Subsets: MEDLINE |
| Imprint Name(s): | Publication: Washington, DC : published on behalf of the Gerontological Society of America by Oxford University Press Original Publication: Washington, DC : Gerontological Society of America, c1995- |
| MeSH Terms: | Natural Language Processing* , Delirium*/diagnosis , Electronic Health Records*, Humans ; Clinical Trials as Topic |
| 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. (© The Author(s) 2025. Published by Oxford University Press on behalf of the Gerontological Society of America. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com .) |
| Grant Information: | R33 AG071744 United States AG NIA NIH HHS; UL1TR003163 NIH NCATS CTSA; UM1 TR004906 United States TR NCATS NIH HHS; R01 AG060993 United States AG NIA NIH HHS; R01 AG068007 United States AG NIA NIH HHS; R33 AG058738 United States AG NIA NIH HHS; R01 AG058639 United States AG NIA NIH HHS; R01 LM011934 United States LM NLM NIH HHS; IO1 RX002992 United States VA VA; T32 GM135094 United States GM NIGMS NIH HHS; RR230020 Ingram Chair in Surgical Sciences, Cancer Prevention and Research Institute of Texas; the Mayo Clinic Robert and Arlene Kogod Center on Aging |
| Contributed Indexing: | Keywords: Artificial Intelligence; Delirium; Electronic Health Records; Natural Language Processing; Translational AI |
| Entry Date(s): | Date Created: 20250929 Date Completed: 20251117 Latest Revision: 20251119 |
| Update Code: | 20251119 |
| PubMed Central ID: | PMC12622219 |
| DOI: | 10.1093/gerona/glaf207 |
| PMID: | 41017643 |
| Database: | MEDLINE |
Nájsť tento článok vo Web of Science | 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.<br />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.<br />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.<br />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.<br /> (© The Author(s) 2025. Published by Oxford University Press on behalf of the Gerontological Society of America. All rights reserved. For commercial re-use, please contact reprints@oup.com for reprints and translation rights for reprints. All other permissions can be obtained through our RightsLink service via the Permissions link on the article page on our site—for further information please contact journals.permissions@oup.com .) |
|---|---|
| ISSN: | 1758-535X |
| DOI: | 10.1093/gerona/glaf207 |