Other Titles
Enhancing Nursing Narrative Interoperability OMOP-CDM Representation of Nursing Observation Features [Title Slide]
Abstract
Purpose: This study aims to standardize inpatient nursing narratives by mapping their semantic units to CONCERN features and implementing a structured, interoperable representation of nursing documentation within the OMOP-CDM.
Background: Nursing narratives capture nuanced assessments, clinical reasoning, and early signs of deterioration, yet remain unstructured and inconsistently represented across institutions, limiting interoperability and secondary use. The OMOP Common Data Model (CDM) provides a standardized framework for harmonizing clinical data, but nursing documentation has not been systematically incorporated. The CONCERN framework, developed to identify early deterioration signals from narrative nursing data, offers an appropriate conceptual basis. This study adopted CONCERN features as standardized terminology to structure inpatient nursing narratives within the CDM environment.
Methods: We designed a CONCERN extension table within the OMOP-CDM and defined metadata elements such as unique note ID, date, note title, concern feature, and source value for nursing records. Nursing narratives were reorganized into standardized categories (e.g., nursing assessment, nursing action, subjective complaints) for consistent use as note title and segmented into sentence-level units representing discrete nursing attributes. Each attribute was semantically mapped to a CONCERN feature and encoded as a custom OMOP concept. Two expert nurses annotated a subset to create a gold-standard reference, followed by clinical team validation. A hybrid rule-based and LLM-driven multilabel classification pipeline (ChatGPT-OS) enabled large-scale automated labeling.
Results: A total of 2,849 distinct sentence-level nursing attributes were identified and mapped to corresponding CONCERN features. The hybrid pipeline showed high agreement with the expert gold-standard, supporting its reliability. Standardizing nursing narratives into consistent note title categories enabled direct linkage between the NOTE table and the CONCERN table. A concern feature flag was added to facilitate identification of deterioration-related content.
Conclusion: Standardizing the semantic structure of nursing narratives within the OMOP-CDM improves interoperability, strengthens patient-level profiles, and supports multi-domain analytical workflows. This structured format enhances the analytic value of nursing text and provides a foundation for future research.
Notes
Presenter notes available in attached slide deck. To see the notes in Adobe Acrobat, go to Tools > Comment or look at your Layers Panel. If the notes were saved as comments or layers, you can toggle them visible.
References:
Gan, S., et al. (2024). "Enhancing readmission prediction models by integrating insights from home healthcare notes: Retrospective cohort study." International journal of nursing studies 158: 104850.
Häyrinen, K., et al. (2010). "Evaluation of electronic nursing documentation—Nursing process model and standardized terminologies as keys to visible and transparent nursing." International journal of medical informatics 79(8): 554-564.
Hripcsak, G., et al. (2015). "Observational Health Data Sciences and Informatics (OHDSI): opportunities for observational researchers." Studies in health technology and informatics 216: 574.
OHDSI (2019). The Book of OHDSI: Observational Health Data Sciences and Informatics, OHDSI.
Rossetti, S. C., et al. (2025). "Real-time surveillance system for patient deterioration: a pragmatic cluster-randomized controlled trial." Nature Medicine 31(6): 1895-1902.
Sigma Membership
Non-member
Type
Presentation
Format Type
Text-based Document
Study Design/Type
Other
Research Approach
Other
Keywords:
Academic-Clinical Partnership, Instrument and Tool Development, Interprofessional, Interdisciplinary, Narratives
Recommended Citation
Gan, Sujin; Park, Rae Woong; and Lee, Youngjin, "Enhancing Nursing Narrative Interoperability: OMOP-CDM Representation of CONCERN Features" (2026). International Nursing Research Congress (INRC). 170.
https://www.sigmarepository.org/inrc/2026/presentations_2026/170
Conference Name
37th International Nursing Research Congress
Conference Host
Sigma Theta Tau International
Conference Location
Toronto, Ontario, Canada
Conference Year
2026
Rights Holder
All rights reserved by the author(s) and/or publisher(s) listed in this item record unless relinquished in whole or part by a rights notation or a Creative Commons License present in this item record. All permission requests should be directed accordingly and not to the Sigma Repository. All submitting authors or publishers have affirmed that when using material in their work where they do not own copyright, they have obtained permission of the copyright holder prior to submission and the rights holder has been acknowledged as necessary.
Review Type
Abstract Review Only: Reviewed by Event Host
Acquisition
Proxy-submission
Date of Issue
2026-08-20
Enhancing Nursing Narrative Interoperability: OMOP-CDM Representation of CONCERN Features
Toronto, Ontario, Canada
Purpose: This study aims to standardize inpatient nursing narratives by mapping their semantic units to CONCERN features and implementing a structured, interoperable representation of nursing documentation within the OMOP-CDM.
Background: Nursing narratives capture nuanced assessments, clinical reasoning, and early signs of deterioration, yet remain unstructured and inconsistently represented across institutions, limiting interoperability and secondary use. The OMOP Common Data Model (CDM) provides a standardized framework for harmonizing clinical data, but nursing documentation has not been systematically incorporated. The CONCERN framework, developed to identify early deterioration signals from narrative nursing data, offers an appropriate conceptual basis. This study adopted CONCERN features as standardized terminology to structure inpatient nursing narratives within the CDM environment.
Methods: We designed a CONCERN extension table within the OMOP-CDM and defined metadata elements such as unique note ID, date, note title, concern feature, and source value for nursing records. Nursing narratives were reorganized into standardized categories (e.g., nursing assessment, nursing action, subjective complaints) for consistent use as note title and segmented into sentence-level units representing discrete nursing attributes. Each attribute was semantically mapped to a CONCERN feature and encoded as a custom OMOP concept. Two expert nurses annotated a subset to create a gold-standard reference, followed by clinical team validation. A hybrid rule-based and LLM-driven multilabel classification pipeline (ChatGPT-OS) enabled large-scale automated labeling.
Results: A total of 2,849 distinct sentence-level nursing attributes were identified and mapped to corresponding CONCERN features. The hybrid pipeline showed high agreement with the expert gold-standard, supporting its reliability. Standardizing nursing narratives into consistent note title categories enabled direct linkage between the NOTE table and the CONCERN table. A concern feature flag was added to facilitate identification of deterioration-related content.
Conclusion: Standardizing the semantic structure of nursing narratives within the OMOP-CDM improves interoperability, strengthens patient-level profiles, and supports multi-domain analytical workflows. This structured format enhances the analytic value of nursing text and provides a foundation for future research.
Description
This study standardized inpatient nursing narratives by mapping sentence-level attributes to CONCERN features and implementing them as structured concepts in the OMOP-CDM. A hybrid expert–LLM pipeline enabled scalable semantic labeling. The resulting CONCERN-CDM provides a unified nursing semantic layer, supports interoperable linkage with clinical domains, enhances analytic readiness, and facilitates research on nursing research.