Artificial intelligence and machine learning for predicting acute kidney injury in severely burned patients: A proof of concept

Nam Tran, Soman Sen, Tina L Palmieri, Kelly Lima, Stephanie Falwell, Jeffery Wajda, Hooman Rashidi

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

Background: Burn critical care represents a high impact population that may benefit from artificial intelligence and machine learning (ML). Acute kidney injury (AKI) recognition in burn patients could be enhanced by ML. The goal of this study was to determine the theoretical performance of ML in augmenting AKI recognition. Methods: We developed ML models using the k-nearest neighbor (k-NN) algorithm. The ML models were trained-tested with clinical laboratory data for 50 adult burn patients that had neutrophil gelatinase associated lipocalin (NGAL), urine output (UOP), creatinine, and N-terminal B-type natriuretic peptide (NT-proBNP) measured within the first 24 h of admission. Results: Half of patients (50%) in the dataset experienced AKI within the first week following admission. ML models containing NGAL, creatinine, UOP, and NT-proBNP achieved 90–100% accuracy for identifying AKI. ML models containing only NT-proBNP and creatinine achieved 80–90% accuracy. Mean time-to-AKI recognition using UOP and/or creatinine alone was achieved within 42.7 ± 23.2 h post-admission vs. within 18.8 ± 8.1 h via the ML-algorithm. Conclusions: The performance of UOP and creatinine for predicting AKI could be enhanced by with a ML algorithm using a k-NN approach when NGAL is not available. Additional studies are needed to verify performance of ML for burn-related AKI.

Original languageEnglish (US)
JournalBurns
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Artificial Intelligence
Acute Kidney Injury
Creatinine
Urine
Machine Learning
Brain Natriuretic Peptide
Critical Care
Burns

Keywords

  • Algorithm
  • Creatinine
  • k-Nearest neighbor
  • Neutrophil gelatinase associated lipocalin
  • Urine output

ASJC Scopus subject areas

  • Surgery
  • Emergency Medicine
  • Critical Care and Intensive Care Medicine

Cite this

@article{86902f02e07248d8a8841c4687a957d5,
title = "Artificial intelligence and machine learning for predicting acute kidney injury in severely burned patients: A proof of concept",
abstract = "Background: Burn critical care represents a high impact population that may benefit from artificial intelligence and machine learning (ML). Acute kidney injury (AKI) recognition in burn patients could be enhanced by ML. The goal of this study was to determine the theoretical performance of ML in augmenting AKI recognition. Methods: We developed ML models using the k-nearest neighbor (k-NN) algorithm. The ML models were trained-tested with clinical laboratory data for 50 adult burn patients that had neutrophil gelatinase associated lipocalin (NGAL), urine output (UOP), creatinine, and N-terminal B-type natriuretic peptide (NT-proBNP) measured within the first 24 h of admission. Results: Half of patients (50{\%}) in the dataset experienced AKI within the first week following admission. ML models containing NGAL, creatinine, UOP, and NT-proBNP achieved 90–100{\%} accuracy for identifying AKI. ML models containing only NT-proBNP and creatinine achieved 80–90{\%} accuracy. Mean time-to-AKI recognition using UOP and/or creatinine alone was achieved within 42.7 ± 23.2 h post-admission vs. within 18.8 ± 8.1 h via the ML-algorithm. Conclusions: The performance of UOP and creatinine for predicting AKI could be enhanced by with a ML algorithm using a k-NN approach when NGAL is not available. Additional studies are needed to verify performance of ML for burn-related AKI.",
keywords = "Algorithm, Creatinine, k-Nearest neighbor, Neutrophil gelatinase associated lipocalin, Urine output",
author = "Nam Tran and Soman Sen and Palmieri, {Tina L} and Kelly Lima and Stephanie Falwell and Jeffery Wajda and Hooman Rashidi",
year = "2019",
month = "1",
day = "1",
doi = "10.1016/j.burns.2019.03.021",
language = "English (US)",
journal = "Burns",
issn = "0305-4179",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Artificial intelligence and machine learning for predicting acute kidney injury in severely burned patients

T2 - A proof of concept

AU - Tran, Nam

AU - Sen, Soman

AU - Palmieri, Tina L

AU - Lima, Kelly

AU - Falwell, Stephanie

AU - Wajda, Jeffery

AU - Rashidi, Hooman

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Background: Burn critical care represents a high impact population that may benefit from artificial intelligence and machine learning (ML). Acute kidney injury (AKI) recognition in burn patients could be enhanced by ML. The goal of this study was to determine the theoretical performance of ML in augmenting AKI recognition. Methods: We developed ML models using the k-nearest neighbor (k-NN) algorithm. The ML models were trained-tested with clinical laboratory data for 50 adult burn patients that had neutrophil gelatinase associated lipocalin (NGAL), urine output (UOP), creatinine, and N-terminal B-type natriuretic peptide (NT-proBNP) measured within the first 24 h of admission. Results: Half of patients (50%) in the dataset experienced AKI within the first week following admission. ML models containing NGAL, creatinine, UOP, and NT-proBNP achieved 90–100% accuracy for identifying AKI. ML models containing only NT-proBNP and creatinine achieved 80–90% accuracy. Mean time-to-AKI recognition using UOP and/or creatinine alone was achieved within 42.7 ± 23.2 h post-admission vs. within 18.8 ± 8.1 h via the ML-algorithm. Conclusions: The performance of UOP and creatinine for predicting AKI could be enhanced by with a ML algorithm using a k-NN approach when NGAL is not available. Additional studies are needed to verify performance of ML for burn-related AKI.

AB - Background: Burn critical care represents a high impact population that may benefit from artificial intelligence and machine learning (ML). Acute kidney injury (AKI) recognition in burn patients could be enhanced by ML. The goal of this study was to determine the theoretical performance of ML in augmenting AKI recognition. Methods: We developed ML models using the k-nearest neighbor (k-NN) algorithm. The ML models were trained-tested with clinical laboratory data for 50 adult burn patients that had neutrophil gelatinase associated lipocalin (NGAL), urine output (UOP), creatinine, and N-terminal B-type natriuretic peptide (NT-proBNP) measured within the first 24 h of admission. Results: Half of patients (50%) in the dataset experienced AKI within the first week following admission. ML models containing NGAL, creatinine, UOP, and NT-proBNP achieved 90–100% accuracy for identifying AKI. ML models containing only NT-proBNP and creatinine achieved 80–90% accuracy. Mean time-to-AKI recognition using UOP and/or creatinine alone was achieved within 42.7 ± 23.2 h post-admission vs. within 18.8 ± 8.1 h via the ML-algorithm. Conclusions: The performance of UOP and creatinine for predicting AKI could be enhanced by with a ML algorithm using a k-NN approach when NGAL is not available. Additional studies are needed to verify performance of ML for burn-related AKI.

KW - Algorithm

KW - Creatinine

KW - k-Nearest neighbor

KW - Neutrophil gelatinase associated lipocalin

KW - Urine output

UR - http://www.scopus.com/inward/record.url?scp=85067475306&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067475306&partnerID=8YFLogxK

U2 - 10.1016/j.burns.2019.03.021

DO - 10.1016/j.burns.2019.03.021

M3 - Article

AN - SCOPUS:85067475306

JO - Burns

JF - Burns

SN - 0305-4179

ER -