Logo image
Back
Predicting Nephrotoxic Acute Kidney Injury in Hospitalized Adults: A Machine Learning Algorithm
Journal article   Open access   Peer reviewed

Predicting Nephrotoxic Acute Kidney Injury in Hospitalized Adults: A Machine Learning Algorithm

Benjamin R. Griffin, Avinash Mudireddy, Benjamin D. Horne, Michel Chonchol, Stuart L. Goldstein, Michihiko Goto, Michael E. Matheny, W. Nick Street, Mary Vaughan-Sarrazin, Diana I. Jalal, …
Kidney medicine, Vol.6(12), 100918
12/2024
DOI: 10.1016/j.xkme.2024.100918
PMCID: PMC11615141
PMID: 39634332
url
https://doi.org/10.1016/j.xkme.2024.100918View
Published (Version of record) Open Access

Abstract

Acute kidney injury (AKI) is a common complication among hospitalized adults, but AKI prediction and prevention among adults has proved challenging. We used machine learning to update the Nephrotoxic Injury Negated by Just-in Time Action (NINJA), a pediatric program that predicts nephrotoxic AKI, to improve accuracy among adults. Retrospective Cohort Study Adults admitted for >48 hours to the University of Iowa Hospital from 2017-2022 NINJA high nephrotoxin exposure (≥3 nephrotoxins on 1 day or intravenous aminoglycoside or vancomycin for ≥3 days). AKI within 48 hours of high-nephrotoxin exposure. We collected 85 variables including demographics, labs, vital signs, and medications. AKI was defined as a serum creatinine increase of ≥0.3 mg/dL. A gated recurrent unit (GRU)-based recurrent neural network (RNN) was trained on 85% of the data, and then tested on the remaining 15%. Model performance was evaluated with precision, recall, negative predictive value, and area under the curve. We used an artificial neural network (ANN) to determine risk factor importance. There were 14,480 patients, 18,180 admissions, and 37,300 high-nephrotoxin exposure events meeting inclusion criteria. In the testing cohort, 29% of exposures developed AKI within 48 hours. The RNN-GRU model predicted AKI with a precision of 0.60, reducing the number of false alerts from 2.5 to 0.7 per AKI case. Lowest hemoglobin, lowest blood pressure, and highest white blood cell count were the most important variables in the ANN model. Acyclovir, piperacillin-tazobactam, calcineurin inhibitors, and ACEi/ARBs were the most important medications. Clinical variables and medications not exhaustive, drug levels or dosing not incorporated, Iowa’s racial makeup may limit generalizability. Our RNN-GRU model substantially reduced the number of false alerts for nephrotoxic AKI, which may facilitate NINJA translation to adult hospitals by providing more targeted intervention.
 Machine Learning Drug-Induced Acute Kidney Injury Nephrotoxicity

Details

Metrics

11 Record Views
3 Times Cited - Web of Science
Logo image