Implementation of an AI-Based Clinical Decision Support System Predicting In-Hospital Cardiac Arrest in General...

Background/Objectives: In-hospital cardiac arrest (IHCA) remains a devastating event associated with high morbidity and mortality among general ward patients. While Rapid Response Systems (RRS) can help identify deteriorating patients, maintaining these systems in secondary hospitals is frequently hindered by severe fiscal and personnel constraints. Consequently, evidence regarding the real-world clinical effectiveness of artificial intelligence software as a medical device (AI-SaMD) for predicting deterioration in such resource-constrained settings remains limited. Methods: We conducted a retrospective analysis on a multicenter, staggered-implementation study evaluating 164,761 eligible adult general ward admissions across three secondary hospitals in South Korea. The intervention involved deploying an AI-SaMD (DeepCARS), which utilizes four routine vital signs to predict ward IHCA within 24 h. The primary outcome was ward IHCA. Secondary outcomes included in-hospital mortality and length of stay (LOS). Exploratory analyses investigated the mechanisms of clinical outcomes by evaluating lead-times to interventions, outcomes in sepsis subgroups, changes in care directives, and post-arrest neurological outcomes. Results: AI-SaMD implementation was associated with a 21% reduction in ward IHCA incidence (adjusted rate ratio 0.79; 95% CI, 0.65-0.96; p = 0.016) and a 15% reduction in in-hospital mortality (aRR 0.85; 95% CI, 0.79-0.90; p < 0.001), alongside significantly shorter hospital and intensive care unit LOS. These associations were also observed in patients with sepsis (IHCA aRR 0.71; 95% CI, 0.54-0.93; p = 0.013). Lead-times to critical care intervention and to antibiotic escalation were numerically shorter in the AI-SaMD group by 16.3 h (p = 0.066) and 2.6 h (p = 0.523); poor neurological outcome at discharge among ward IHCA cases was 85/108 (78.7%) in the AI-SaMD group versus 63/102 (61.8%) in the standard-care group (aRR 1.13; 95% CI, 0.99-1.33; p = 0.058); and the full-code death rate did not differ between groups (aRR 0.94; 95% CI, 0.76-1.15)-none of these additional analyses reached statistical significance. Conclusions: In secondary hospitals unable to operate an RRS due to fiscal limitations, implementation of an AI-SaMD as an additional informational layer was associated with lower ward IHCA and in-hospital mortality. The AI-SaMD may serve as an actionable and scalable additional safety layer for general-ward patients in resource-constrained environments where RRS infrastructure is not feasible. Although this was a multicenter, large-scale study, the present analysis was retrospective and quasi-experimental in design; rigorous randomized studies are needed to confirm these associations.