EUVIMEDOpdag EUVIMED
Randomisierte kontrollierte StudieStudienprotokollOpen access

Clinical Effectiveness of AI-Based Cardiac Arrest Prediction System for General Ward Patients (VITAL-MD): Protocol for a Multicenter Pragmatic Stepped Wedge Cluster Randomized Controlled Trial

Klinische Wirksamkeit eines KI-basierten Systems zur Vorhersage von Herzstillstand bei Patient:innen auf Allgemeinstationen (VITAL-MD): Protokoll für eine multizentrische pragmatische gestufte Cluster-randomisierte kontrollierte Studie

Mincheol Kim, Kyung Hoon Kim, Minsoo Kim, Sun Jung Kwon, Myung Soo Park, Ah Jin Kim, Man-Jong Lee, Mi Hwa Park, Hyung Keun Cha, Minhyeok Lee, In Beom Jeong, Soon Joo Wang and 10 more

JMIR Research Protocols · 2026-10-19 · 15 · e104230-e104230

DOI: 10.2196/104230 ↗

Auf einen Blick

Das Protokoll beschreibt eine multizentrische SW-CRT zur Prüfung von VUNO Med-DeepCARS auf Allgemeinstationen. Primärer Endpunkt ist die Inzidenz von IHCA; Ergebnisse liegen noch nicht vor.

Fragestellung

Reduziert die Implementierung von VUNO Med-DeepCARS als eigenständiges klinisches Entscheidungsunterstützungstool im Routinebetrieb den IHCA gegenüber der üblichen Versorgung?

Methode

Pragmatische multizentrische SW-CRT an 4 universitären Krankenhäusern in der Republik Korea; Erwachsene ab 19 Jahren auf Allgemeinstationen; 4 Übergänge mit 7-tägigen Washout-Perioden; ITT-Analyse mit generalisierten linearen Mixed Models.

Ergebnisse

Die Studie ist registriert (KCT0010243). Rekrutierung: 1. April 2025 bis 31. März 2026. Alle 4 Standorte wechselten in die Postimplementierungsphase; Primärergebnisse werden für 2027 erwartet.

Schlussfolgerung der Autor:innen

VITAL-MD soll die erste große multizentrische randomisierte Evidenz dazu liefern, ob ein KI-EWS als eigenständiges Gerät in externer Validierung die patientenbezogenen Ergebnisse bei Allgemeinstationspatient:innen verbessert.

Kernaussagen

  • Protokoll einer multizentrischen pragmatischen SW-CRT
  • Primärer Endpunkt: IHCA-Inzidenz in der Zielkohorte
  • Primärergebnisse werden für 2027 erwartet

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Randomisierte kontrollierte Studie in JMIR Research Protocols, published online on 2026-10-19. Written by Mincheol Kim and 21 co-authors. Institution: VUNO, Seoul, Republic of Korea. Major MEDLINE topics: Heart Arrest, Artificial Intelligence. 63 references. The full text is freely available in PubMed Central.

Auf einen BlickAbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

Background

In-hospital cardiac arrest (IHCA) remains a frequent and devastating event, and conventional early warning scores (EWSs) coupled with rapid response systems (RRSs) have shown inconsistent effects on patient-centered outcomes, largely owing to limited predictive accuracy and high false-alarm burden. AI-based EWSs (AI-EWSs) have demonstrated superior discrimination retrospectively, but high-quality prospective evidence in true external validation environments remains scarce. Existing AI-EWS trials have either been confined to internal-development settings or bundled the algorithm with specific implementation infrastructure, leaving the stand-alone effect of AI-based software as a medical device (AI-SaMD) on patient outcomes uncharacterized.

Objective

This trial will evaluate whether implementation of AI-SaMD (VUNO Med -DeepCARS ) as a stand-alone clinical decision-support tool in routine general-ward care reduces IHCA compared with usual care based on conventional EWSs.

Methods

The VITAL-MD trial (validation of an AI-based clinical deterioration prediction model on patient outcomes through a stepped-wedge cluster randomized trial [SW-CRT] multicenter evaluation of DeepCARS) is a pragmatic, multicenter, SW-CRT conducted at 4 tertiary academic hospitals in the Republic of Korea. Six tertiary academic hospitals were assessed for eligibility based on inpatient capacity, RRS operating hours aligned with the national RRS pilot program, and no prior AI-SaMD use. All adult patients aged 19 years or older admitted to general wards during the 12-month trial period are included; patients younger than 19 years, or with no documented vital signs throughout hospitalization, are excluded. The 4 sites are randomized to sequentially transition from preimplementation (usual care) to postimplementation (AI-SaMD–guided care) in 4 steps separated by 7-day washout periods. DeepCARS generates real-time risk scores from 4 vital signs and integrates into the existing electronic medical record interface without altering RRS workflows. The primary outcome is the incidence of general-ward IHCA, defined per the Utstein guidelines, among the target cohort (defined as patients exceeding the alert threshold at least once). Assuming a baseline IHCA incidence of 6.70%, a 40% relative risk reduction, an intracluster correlation coefficient of 0.01, and 350 patients per cluster-period, 7002 target-cohort patients (total enrollment approximately 72,695) provide 80% power. Analyses follow the intention-to-treat principle using generalized linear mixed models adjusting for prespecified covariates, with prespecified sensitivity, subgroup, and compliance analyses.

Results

The trial was registered with the Clinical Research Information Service (KCT0010243) on February 28, 2025. Recruitment was conducted from April 1, 2025, to March 31, 2026. All 4 sites completed transition to the postimplementation period, and data cleaning is currently underway before the final database lock, with primary results expected in 2027.

Conclusions

VITAL-MD will provide the first large-scale, multicenter randomized evidence evaluating whether an AI-EWS, deployed as a stand-alone device in external validation environments and benchmarked against real-world standard-of-care practice, improves patient-centered outcomes for general-ward patients, advancing the evaluation of AI-SaMD from retrospective diagnostic accuracy toward prospective, action-anchored clinical utility.

Subjects

MeSH terms (MEDLINE)

Heart ArrestArtificial IntelligenceHumansMulticenter Studies as TopicPragmatic Clinical Trials as TopicEarly Warning ScoreRandomized Controlled Trials as TopicPatients' Rooms

Author keywords

artificial intelligenceclinical decision support systemsclinical deteriorationdeep learningearly warning scorein-hospital cardiac arrestpatient-centered outcomerandomized controlled trialrapid response systemrapid response team

Authors and institutions

  • VUNO, Seoul, Republic of Korea.
  • Department of Digital Health, Samsung Advanced Institute for Health Sciences & Technology, Sungkyunkwan University, Seoul, Republic of Korea.
  • Department of Internal Medicine, Division of Pulmonary and Critical Care Medicine, College of Medicine, Incheon St. Mary's Hospital, The Catholic University of Korea, Incheon, Republic of Korea.
  • Department of Internal Medicine, Division of Pulmonology and Critical Care Medicine, College of Medicine, Konyang University Hospital, Konyang University, Daejeon, Republic of Korea.
  • Department of Cardiology, College of Medicine, Dongtan Sacred Heart Hospital, Hallym University, Hwaseong, Gyeonggi-do, Republic of Korea.
  • Department of Critical Care Medicine, Inha University Hospital, 27 Inhang-ro, Jung-gu, Incheon, 22332, Republic of Korea, 82 32-890-2114, 82 32-890-2114.

Cite

APA

Kim, M., Kim, K. H., Kim, M., Kwon, S. J., Park, M. S., Kim, A. J., Lee, M. J., Park, M. H., Cha, H. K., Lee, M., Jeong, I. B., Wang, S. J., An, S. B., Lee, J. H., Cho, K. J., Jang, J., Jeong, H., Lee, Y. Y., Han, W., …, & Yoo, D. (2026). Clinical Effectiveness of AI-Based Cardiac Arrest Prediction System for General Ward Patients (VITAL-MD): Protocol for a Multicenter Pragmatic Stepped Wedge Cluster Randomized Controlled Trial. JMIR Research Protocols, 15, e104230-e104230. https://doi.org/10.2196/104230

Vancouver

Kim M, Kim KH, Kim M, Kwon SJ, Park MS, Kim AJ, et al. Clinical Effectiveness of AI-Based Cardiac Arrest Prediction System for General Ward Patients (VITAL-MD): Protocol for a Multicenter Pragmatic Stepped Wedge Cluster Randomized Controlled Trial. JMIR Research Protocols. 2026;15:e104230-e104230. doi:10.2196/104230

BibTeX
@article{Kim2026,
  author = {Kim, Mincheol and Kim, Kyung Hoon and Kim, Minsoo and Kwon, Sun Jung and Park, Myung Soo and Kim, Ah Jin and Lee, Man-Jong and Park, Mi Hwa and Cha, Hyung Keun and Lee, Minhyeok and Jeong, In Beom and Wang, Soon Joo and An, Sung Bak and Lee, Jeen Hwa and Cho, Kyung-Jae and Jang, Jinhui and Jeong, HyoJin and Lee, Yoon Young and Han, Woori and VITAL-MD Study Group, VITAL-MD Study Group and Kim, Jung Soo and Yoo, Dongjoon},
  title = {Clinical Effectiveness of AI-Based Cardiac Arrest Prediction System for General Ward Patients (VITAL-MD): Protocol for a Multicenter Pragmatic Stepped Wedge Cluster Randomized Controlled Trial},
  journal = {JMIR Research Protocols},
  year = {2026},
  volume = {15},
  pages = {e104230--e104230},
  doi = {10.2196/104230}
}
Start for free →