JMIR Publications

ABSTRACT

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 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 standalone effect of an AI–based software as a medical device (AI-SaMD) on patient outcomes uncharacterized.

Objective:

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

Methods:

The VITAL-MD trial is a pragmatic, multicenter, stepped-wedge cluster randomized trial (SW-CRT) conducted at four tertiary academic hospitals in the Republic of Korea, conducted among six tertiary academic hospitals 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 (≥19 years) admitted to general wards during the 12-month trial period are included; patients aged <19 years or with no documented vital signs throughout hospitalization are excluded. The four sites are randomized to sequentially transition from pre-implementation (usual care) to post-implementation (AI-SaMD–guided care) in four steps separated by 7-day washout periods. DeepCARS® generates real-time risk scores from four 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 (patients exceeding the alert threshold at least once). Assuming a baseline IHCA incidence of 6.70%, a 40% relative risk reduction, intra-cluster correlation of 0.01, and 350 patients per cluster-period, 7,002 target-cohort patients (total enrollment ~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 ran from April 1, 2025 to March 31, 2026; all four sites completed transition to the post-implementation period, and data cleaning is currently underway prior to final database lock, with primary results expected in 2027.

Conclusions:

VITAL-MD will provide the first large-scale multicenter randomized evidence on whether an AI-EWS, deployed as a standalone device in external-validation environments and benchmarked against real-world standard-of-care practice, can improve patient-centered outcomes for general-ward patients, advancing AI-SaMD evaluation from retrospective diagnostic accuracy toward prospective, action-anchored clinical utility. Clinical Trial: Clinical Research Information Service (CRIS) of the Republic of Korea, KCT0010243 (Registered on 2025-02-28); https://cris.nih.go.kr/cris/search/detailSearch.do?seq=34373