Skip Navigation
Skip to contents

J Korean Acad Nurs : Journal of Korean Academy of Nursing

Search
Advanced Search
Korean Society of Nursing Science
OPEN ACCESS
mobile search button mobile menu button

Articles

Page Path
HOME > J Korean Acad Nurs > Volume 56(2); 2026 > Article
Editorial
Toward an end-to-end K-AI nursing ecosystem: digital twins across the care continuum
Jeung-Im Kim1orcid, Jiyeon Kang2orcid, YeoJin Im3orcid, Sung Reul Kim4orcid, Sun Ju Chang5orcid
Journal of Korean Academy of Nursing 2026;56(2):123-125.
DOI: https://doi.org/10.4040/jkan.25180
Published online: April 17, 2026

1School of Nursing, Soonchunhyang University College of Medicine, Cheonan, South Korea

2College of Nursing, Dong-A University, Busan, South Korea

3College of Nursing Science, Kyung Hee University, Seoul, South Korea

4College of Nursing, Korea University, Seoul, South Korea

5College of Nursing, Seoul National University, Seoul, South Korea

Corresponding author: Sun Ju Chang College of Nursing, Seoul National University, 103 Daehak-ro, Jongno-gu, Seoul 03080, South Korea E-mail: changsj@snu.ac.kr
• Received: December 28, 2025   • Revised: December 31, 2025   • Accepted: December 31, 2025

© 2026 Korean Society of Nursing Science

This is an Open Access article distributed under the terms of the Creative Commons Attribution NoDerivs License (http://creativecommons.org/licenses/by-nd/4.0) If the original work is properly cited and retained without any modification or reproduction, it can be used and re-distributed in any format and medium.

  • 2,722 Views
  • 158 Download
  • 1 Crossref
next
Full Article

Download PDF Download PDF

Artificial intelligence (AI) and digital health technologies are rapidly entering Korean healthcare, yet many nursing units still function as “human-buffered” systems under chronic workforce shortages. The Korean Health Industry Development Institute and the K-Future Health Initiative are calling for proposals to address national health challenges. In response, our planning committee identified five nursing-sensitive populations—high-risk pregnant women, children with chronic illness, critically ill patients, people with complex neurological conditions, and older adults with disabilities—where digital tools could fundamentally redesign care. We propose how a Korean AI nurse (K-AI nurse) and digital twin framework could address their shared vulnerabilities.
Korea faces rising rates of advanced maternal age and medically complicated pregnancies amid historically low fertility. Preterm birth is a major public health crisis; preterm infants face elevated risks of early death, neurodevelopmental impairment, and chronic disease, while families shoulder substantial medical and psychosocial costs. Yet prenatal care still relies on intermittent clinic visits and ultrasound examinations. Invisible changes—pregnancy-related stress, heart rate variability (HRV), sleep and activity patterns, and subtle cervical remodeling—are rarely tracked in real time. Recent AI advances enable continuous collection of HRV, sleep, and activity data via wearables and smartphone apps, which can be integrated with conventional clinical indicators for earlier, more precise prediction of preterm birth risk [1]. We therefore propose viewing pregnancy as a time-limited but highly vulnerable “functional disability” state requiring nurse-led digital monitoring in the community. A K-AI nurse would use digital twin models to integrate stress scales, HRV, circadian rhythms, and cervical indices, generating timely alerts and tailored self-care and referral recommendations.
Children with asthma, diabetes, and other chronic conditions experience acute vulnerability around hospital discharge, when responsibility for complex care suddenly shifts to families [2]. Information gaps, fragmented follow-up, and caregivers’ fear of missing subtle deterioration are common. We envision a multimodal, explainable AI “care coordinator” for these children and families. This digital twin–informed system would analyze respiratory sounds, continuous glucose data, sleep patterns, vocal features, and caregiver reports together, using large language models to stratify urgency in real time and provide step-by-step home management guidance [3]. By making recommendations transparent and adjustable, the system could support shared decision-making, reduce unnecessary emergency visits, and identify caregiver burnout early through patterns in language and interaction.
The COVID-19 (coronavirus disease 2019) crisis highlighted the critical role of intensive care unit (ICU) nurses. Korean ICUs, however, remain chronically under-resourced, with high workloads and turnover. Patients often deviate from textbook trajectories, forcing nurses to rely heavily on tacit knowledge when responding to subtle signs of deterioration. We propose an AI-supported Critical Care Nursing System combining physical automation with digital twin modeling [4]. A physical K-AI nurse—implemented through robotics and smart devices trained on expert nurses’ actions and speech—would standardize and safely offload selected monitoring and routine tasks. In parallel, an ICU digital twin would continuously learn from high-frequency physiological data, medications, and interventions to predict deterioration patterns and recommend nursing priorities. This combination could reduce errors, free nurses for complex relational care, and serve as a high-fidelity simulation tool for educating novice ICU nurses.
People living with Parkinson’s disease and other degenerative neurological disorders face a different but equally serious vulnerability. They transition repeatedly between acute care and community settings, juggling multiple diagnoses, medications, and providers, often with limited guidance on warning signs and when to seek help [5]. A person-level neurological digital twin could integrate clinical histories, imaging, medications, sensor streams, and daily activity data to model interactions across conditions and predict high-risk transition periods [6]. A K-AI nurse could translate these forecasts into individualized care plans, proactive check-ins, and simple decision rules (“if gait speed drops and nighttime agitation rises for 3 days, contact your clinic”). This approach may prove particularly valuable in regions with limited specialist access.
Older adults living with disability carry a “double burden” of age-related decline and functional impairment, often compounded by multimorbidity [7]. Many require 24-hour, judgment-intensive care that current human resources cannot reliably provide. Medication errors, falls, and delayed responses to acute illness are persistent risks. For this group, we imagine a “virtual hospital at home” combining physical and digital K-AI nurses [8]. Environmental sensors, wearable devices, and periodic in-home assessments would feed a digital twin tracking physiological and functional trajectories. Physical assistive robots, guided by AI models of expert nursing practice, could support safe mobility and basic care tasks, while a virtual K-AI nurse coordinates monitoring data, flags early warning signs, and connects patients and families with community resources. Such a model could extend safe aging in place and reduce avoidable institutionalization.
Figure 1 summarizes this vision as a Precision Nursing Intelligence (PNI) Platform linking in-hospital innovation, a central “care-in-the-loop” engine, and post-hospital care modules through hospital–home data loops and wearable/IoT (Internet of Things) streams. Across these five priority populations, the core problem is not only disease itself but vulnerability to rapid, often invisible deterioration. Digital twins and K-AI nurses are designed to extend nurses’ reach, continuity, and situational awareness across settings—not to replace human care.
To realize this vision, Korean nursing science must lead in three critical areas: (1) defining “vulnerability” and “K-AI nurse” in nursing terms; (2) building robust Korean evidence through multicenter cohorts and digital nursing intervention studies so that algorithms truly reflect our people and practice contexts [9,10]; and (3) embedding digital literacy, data interpretation, and AI ethics into education and policy so nurses can shape governance on privacy, bias, and humane care. If we succeed, Korean nursing will co-create a K-AI nursing ecosystem that genuinely protects the dignity and safety of those most at risk.

Conflicts of Interest

Sun Ju Chang serves as Editorial Board members of the Journal of Korean Academy of Nursing but have no role in the decision to publish this article. Except for that, no potential conflict of interest relevant to this article was reported.

Acknowledgements

None.

Funding

None.

Data Sharing Statement

Please contact the corresponding author for data availability.

Author Contributions

Conceptualization: JIK, JK, YJI, SRK, SJC. Formal analysis: JIK, JK, YJI, SRK, SJC. Methodology: JIK, JK, YJI, SRK, SJC. Visualization: SJC. Writing - original draft: JIK, JK, YJI, SRK, SJC. Writing - review & editing: JIK, JK, YJI, SRK, SJC. Validation: JIK, JK, YJI, SRK, SJC.

Figure 1.
Precision nursing intelligence (PNI) platform: end-to-end nursing workflow innovation architecture (AI-generated image in response to the request "visualization of AI-integrated nursing across the care continuum for diverse patient populations" (Generator: Gemini; Requestor: SJC; Date: 2025-12-15). AGI, artificial general intelligence; ICU, intensive care unit.
jkan-25180f1.jpg

Figure & Data

REFERENCES

    Citations

    Citations to this article as recorded by  
    • Workplace-Based Multicomponent Weight Management Interventions for Employees with Overweight or Obesity: A Systematic Review
      Yesol Kim, Seonhye Lee, Haeyoung Min, Sohee Jung, A-young Jo, Hyeonji Kang
      Journal of The Korean Society of Living Environmental System.2026; 33(4): 454.     CrossRef

    • ePub LinkePub Link
    • Cite
      CITE
      export Copy Download
      Close
      Download Citation
      Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.
      Format:
      • RIS — For EndNote, ProCite, RefWorks, and most other reference management software
      • BibTeX — For JabRef, BibDesk, and other BibTeX-specific software
      Include:
      • Citation for the content below
      Toward an end-to-end K-AI nursing ecosystem: digital twins across the care continuum
      J Korean Acad Nurs. 2026;56(2):123-125.   Published online April 17, 2026
      DOI: https://doi.org/10.4040/jkan.25180
      Close
    • XML DownloadXML Download
    Figure
    • 0
    We recommend
    Toward an end-to-end K-AI nursing ecosystem: digital twins across the care continuum
    Image
    Figure 1. Precision nursing intelligence (PNI) platform: end-to-end nursing workflow innovation architecture (AI-generated image in response to the request "visualization of AI-integrated nursing across the care continuum for diverse patient populations" (Generator: Gemini; Requestor: SJC; Date: 2025-12-15). AGI, artificial general intelligence; ICU, intensive care unit.

    Figure 1.

    Toward an end-to-end K-AI nursing ecosystem: digital twins across the care continuum
    J Korean Acad Nurs : Journal of Korean Academy of Nursing
    © Korean Society of Nursing Science.
    Close layer
    TOP