Impact of acute kidney injury labeling strategies in hospitalized patients: suggestion for a dual-alert…

Cohort studyKidney research and clinical practice· Dec 2025

Impact of acute kidney injury labeling strategies in hospitalized patients: suggestion for a dual-alert clinical decision support system.

Se-Jin Ahn, Nam-Jun Cho, Inyong Jeong … Hwamin Lee

Clinical Decision SupportCohort studyQ1IF 2.6

Refined acute kidney injury labeling cut false-positive alerts by 27% with minimal missed cases

Impact of acute kidney injury labeling strategies in hospitalized patients: suggestion for a dual-alert clinical decision support system.

Se-Jin Ahn … Hwamin Lee

Kidney research and clinical practice · Dec 2025

Background

Operational variability in defining acute kidney injury (acute kidney injury) undermines the diagnostic reliability and impairs the generalizability of machine learning (machine learning) models.

Purpose

To assess real-world interpretability, ambiguous cases were reviewed.

Methods

Two conservative refinements to the KDIGO serum creatinine (serum creatinine)-based criteria were proposed: 1) exclusion of transient serum creatinine decreases from baseline estimation and 2) application of a minimum absolute serum creatinine increase threshold.

n = 5,115 patients

Results

27%

false alerts dropped, with almost no true acute kidney injury cases missed

n = 5,115 patients

More results

Among 5,115 patients labeled by the standard KDIGO, 4,137 (80.9%) met the refined criteria, and 978 (19.1%) were considered ambiguous.

Ambiguous cases often reflected transient measurement variability or frailty.

“

Conclusion · 1 of 2

This study presents a strategic acute kidney injury labeling approach based on KDIGO criteria and suggests a dual-alert system to distinguish refined acute kidney injury and ambiguous acute kidney injury cases.

Conclusion · 2 of 2

These approaches may enhance both predictive model performance and clinically meaningful detection.

Impact of acute kidney injury labeling strategies in hospitalized patients: suggestion for a dual-alert clinical decision support system.

Impact of acute kidney injury labeling strategies in hospitalized patients: suggestion for a dual-alert clinical decision support system.

Related papers