UT-AKI

UT-AKI predicts the risk of acute kidney injury (AKI) in ST-elevation myocardial infarction (STEMI) patients to inform clinical risk assessment.


Key Features:

  • Prediction Accuracy: Demonstrates superior sensitivity and overall predictive capability compared to existing indices, with area under the curve (AUC) of 0.76 for distinguishing patients who will develop AKI.
  • Clinical Relevance: Developed from a racially diverse cohort of 1,144 consecutive STEMI patients, identifying Stage ≥1 AKI in 12.9% and Stage 2–3 AKI in 2.9%, with AKI associated with 5.7-fold unadjusted increased mortality, 2.5-fold longer hospital stay, systolic dysfunction, elevated left ventricular end-diastolic pressures, hypotension, and need for intra-aortic balloon counterpulsation.
  • Internal Validation: The algorithm underwent internal validation within the study cohort.

Scientific Applications:

  • Risk Stratification: Identifies patients at increased risk of AKI post-STEMI to enable stratification for intensified monitoring and management.
  • Tailored Interventions: Provides predictive information to support customization of diagnostic and therapeutic strategies aimed at mitigating AKI onset and complications.
  • Resource Allocation: Predicts likelihood of prolonged hospital stay to inform planning and allocation of healthcare resources.

Methodology:

The algorithm was derived by analyzing clinical data from a racially diverse cohort of 1,144 consecutive STEMI patients and correlating clinical parameters with AKI incidence and severity, with internal validation performed within the cohort.

Topics

Details

Tool Type:
web application
Operating Systems:
Linux, Windows, Mac
Added:
6/12/2018
Last Updated:
11/25/2024

Operations

Publications

Zambetti BR, Thomas F, Hwang I, Brown AC, Chumpia M, Ellis RT, Naik D, Khouzam RN, Ibebuogu UN, Reed GL. A web-based tool to predict acute kidney injury in patients with ST-elevation myocardial infarction: Development, internal validation and comparison. PLOS ONE. 2017;12(7):e0181658. doi:10.1371/journal.pone.0181658. PMID:28759604. PMCID:PMC5536350.