JMIR Publications

ABSTRACT

Background:

Acute kidney injury (AKI) is a frequent and serious complication among hospitalized patients, particularly in critical care settings, where its incidence can exceed 50%. AKI is associated with increased mortality, prolonged hospitalization, dialysis dependence, and higher healthcare costs. Although the KDIGO guidelines emphasize supportive care, hemodynamic optimization, and avoidance of nephrotoxins, their implementation remains inconsistent, partly due to the lack of timely risk stratification. Recent advances in artificial intelligence (AI) have enhanced early prediction and detection of AKI, offering new opportunities to improve patient outcomes and ICU efficiency. The U-Care Renal Platform (UCRP), a CE-marked AI-powered medical device, integrates directly with the ICU electronic health record (EHR) to continuously analyze patient data and predict the risk of moderate or severe AKI within 24 hours, providing actionable, guideline-based recommendations. While the predictive performance of UCRP has been validated previously, its real-world impact on clinical and operational outcomes in the ICU remains underexplored.

Objective:

This single-center, pre–post implementation pilot study evaluated the clinical and operational impact of integrating the UCRP into routine ICU practice at SCIAS Hospital, Barcelona.

Methods:

The study was conducted over a 14-month period (March 2023–March 2025) and included 202 post-surgical adult ICU patients. Outcomes of interest were assessed by comparing pre-implementation and post-implementation periods. These included the incidence of moderate-to-severe AKI (KDIGO stages 2–3), the use of nephrotoxic medications, the frequency of hypotensive episodes among AKI patients, and the ICU length of stay.

Results:

Following UCRP implementation, the incidence of moderate-to-severe AKI decreased by 22%, daily nephrotoxic drug administration was reduced by 28%, and hypotensive episodes among AKI patients declined by 33%. Additionally, ICU length of stay decreased by 12% compared with the pre-implementation period.

Conclusions:

Integration of the UCRP into ICU workflows was associated with improved AKI prevention and management, likely by facilitating early risk identification and adherence to KDIGO recommendations. These preliminary findings highlight the potential of AI-driven decision support tools to enhance patient outcomes and clinical efficiency in critical care settings. Further multicenter studies with larger and more heterogeneous cohorts are warranted to validate these results and assess long-term outcomes, including major adverse kidney events. Study limitations include its single-center design, small sample size, and focus on post-surgical ICU patients, which may limit generalizability.