Early Recognition of Burn- and Trauma-Related Acute Kidney Injury: A Pilot Comparison of Machine Learning Techniques

Hooman H. Rashidi, Soman Sen, Tina L. Palmieri, Thomas Blackmon, Jeffery Wajda, Nam K. Tran

Research output: Contribution to journalArticle

Abstract

Severely burned and non-burned trauma patients are at risk for acute kidney injury (AKI). The study objective was to assess the theoretical performance of artificial intelligence (AI)/machine learning (ML) algorithms to augment AKI recognition using the novel biomarker, neutrophil gelatinase associated lipocalin (NGAL), combined with contemporary biomarkers such as N-terminal pro B-type natriuretic peptide (NT-proBNP), urine output (UOP), and plasma creatinine. Machine learning approaches including logistic regression (LR), k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), and deep neural networks (DNN) were used in this study. The AI/ML algorithm helped predict AKI 61.8 (32.5) hours faster than the Kidney Disease and Improving Global Disease Outcomes (KDIGO) criteria for burn and non-burned trauma patients. NGAL was analytically superior to traditional AKI biomarkers such as creatinine and UOP. With ML, the AKI predictive capability of NGAL was further enhanced when combined with NT-proBNP or creatinine. The use of AI/ML could be employed with NGAL to accelerate detection of AKI in at-risk burn and non-burned trauma patients.

Original languageEnglish (US)
Article number205
JournalScientific reports
Volume10
Issue number1
DOIs
StatePublished - Dec 1 2020

Fingerprint

Burns
Acute Kidney Injury
Artificial Intelligence
Wounds and Injuries
Creatinine
Biomarkers
Brain Natriuretic Peptide
Urine
Kidney Diseases
Machine Learning
Logistic Models
Lipocalin-2

ASJC Scopus subject areas

  • General

Cite this

Early Recognition of Burn- and Trauma-Related Acute Kidney Injury : A Pilot Comparison of Machine Learning Techniques. / Rashidi, Hooman H.; Sen, Soman; Palmieri, Tina L.; Blackmon, Thomas; Wajda, Jeffery; Tran, Nam K.

In: Scientific reports, Vol. 10, No. 1, 205, 01.12.2020.

Research output: Contribution to journalArticle

@article{9314383d06af43c78d8ea228e1651771,
title = "Early Recognition of Burn- and Trauma-Related Acute Kidney Injury: A Pilot Comparison of Machine Learning Techniques",
abstract = "Severely burned and non-burned trauma patients are at risk for acute kidney injury (AKI). The study objective was to assess the theoretical performance of artificial intelligence (AI)/machine learning (ML) algorithms to augment AKI recognition using the novel biomarker, neutrophil gelatinase associated lipocalin (NGAL), combined with contemporary biomarkers such as N-terminal pro B-type natriuretic peptide (NT-proBNP), urine output (UOP), and plasma creatinine. Machine learning approaches including logistic regression (LR), k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), and deep neural networks (DNN) were used in this study. The AI/ML algorithm helped predict AKI 61.8 (32.5) hours faster than the Kidney Disease and Improving Global Disease Outcomes (KDIGO) criteria for burn and non-burned trauma patients. NGAL was analytically superior to traditional AKI biomarkers such as creatinine and UOP. With ML, the AKI predictive capability of NGAL was further enhanced when combined with NT-proBNP or creatinine. The use of AI/ML could be employed with NGAL to accelerate detection of AKI in at-risk burn and non-burned trauma patients.",
author = "Rashidi, {Hooman H.} and Soman Sen and Palmieri, {Tina L.} and Thomas Blackmon and Jeffery Wajda and Tran, {Nam K.}",
year = "2020",
month = "12",
day = "1",
doi = "10.1038/s41598-019-57083-6",
language = "English (US)",
volume = "10",
journal = "Scientific Reports",
issn = "2045-2322",
publisher = "Nature Publishing Group",
number = "1",

}

TY - JOUR

T1 - Early Recognition of Burn- and Trauma-Related Acute Kidney Injury

T2 - A Pilot Comparison of Machine Learning Techniques

AU - Rashidi, Hooman H.

AU - Sen, Soman

AU - Palmieri, Tina L.

AU - Blackmon, Thomas

AU - Wajda, Jeffery

AU - Tran, Nam K.

PY - 2020/12/1

Y1 - 2020/12/1

N2 - Severely burned and non-burned trauma patients are at risk for acute kidney injury (AKI). The study objective was to assess the theoretical performance of artificial intelligence (AI)/machine learning (ML) algorithms to augment AKI recognition using the novel biomarker, neutrophil gelatinase associated lipocalin (NGAL), combined with contemporary biomarkers such as N-terminal pro B-type natriuretic peptide (NT-proBNP), urine output (UOP), and plasma creatinine. Machine learning approaches including logistic regression (LR), k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), and deep neural networks (DNN) were used in this study. The AI/ML algorithm helped predict AKI 61.8 (32.5) hours faster than the Kidney Disease and Improving Global Disease Outcomes (KDIGO) criteria for burn and non-burned trauma patients. NGAL was analytically superior to traditional AKI biomarkers such as creatinine and UOP. With ML, the AKI predictive capability of NGAL was further enhanced when combined with NT-proBNP or creatinine. The use of AI/ML could be employed with NGAL to accelerate detection of AKI in at-risk burn and non-burned trauma patients.

AB - Severely burned and non-burned trauma patients are at risk for acute kidney injury (AKI). The study objective was to assess the theoretical performance of artificial intelligence (AI)/machine learning (ML) algorithms to augment AKI recognition using the novel biomarker, neutrophil gelatinase associated lipocalin (NGAL), combined with contemporary biomarkers such as N-terminal pro B-type natriuretic peptide (NT-proBNP), urine output (UOP), and plasma creatinine. Machine learning approaches including logistic regression (LR), k-nearest neighbor (k-NN), support vector machine (SVM), random forest (RF), and deep neural networks (DNN) were used in this study. The AI/ML algorithm helped predict AKI 61.8 (32.5) hours faster than the Kidney Disease and Improving Global Disease Outcomes (KDIGO) criteria for burn and non-burned trauma patients. NGAL was analytically superior to traditional AKI biomarkers such as creatinine and UOP. With ML, the AKI predictive capability of NGAL was further enhanced when combined with NT-proBNP or creatinine. The use of AI/ML could be employed with NGAL to accelerate detection of AKI in at-risk burn and non-burned trauma patients.

UR - http://www.scopus.com/inward/record.url?scp=85077847171&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077847171&partnerID=8YFLogxK

U2 - 10.1038/s41598-019-57083-6

DO - 10.1038/s41598-019-57083-6

M3 - Article

C2 - 31937795

AN - SCOPUS:85077847171

VL - 10

JO - Scientific Reports

JF - Scientific Reports

SN - 2045-2322

IS - 1

M1 - 205

ER -