Development of a neural network model for early detection of creatinine change in critically Ill children

IntroductionRenal dysfunction is common in critically ill children and increases morbidity and mortality risk. Diagnosis and management of renal dysfunction relies on creatinine, a delayed marker of renal injury. We aimed to develop and validate a machine learning model using routinely collected cli...

Full description

Saved in:
Bibliographic Details
Main Authors: Celeste G. Dixon, Eduardo A. Trujillo Rivera, Anita K. Patel, Murray M. Pollack
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-04-01
Series:Frontiers in Pediatrics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fped.2025.1549836/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766647776149504
author Celeste G. Dixon
Eduardo A. Trujillo Rivera
Anita K. Patel
Murray M. Pollack
author_facet Celeste G. Dixon
Eduardo A. Trujillo Rivera
Anita K. Patel
Murray M. Pollack
author_sort Celeste G. Dixon
collection DOAJ
description IntroductionRenal dysfunction is common in critically ill children and increases morbidity and mortality risk. Diagnosis and management of renal dysfunction relies on creatinine, a delayed marker of renal injury. We aimed to develop and validate a machine learning model using routinely collected clinical data to predict 24-hour creatinine change in critically ill children before change is observed clinically.MethodsRetrospective cohort study of 39,932 pediatric intensive care unit encounters in a national multicenter database from 2007 to 2022. A neural network was trained to predict <50% or ≥50% creatinine change in the next 24 h. Admission demographics, routinely measured vital signs, laboratory tests, and medication use variables were used as predictors for the model. Data set was randomly split at the encounter level into model development (80%) and test (20%) sets. Performance and clinical relevance was assessed in the test set by accuracy of prediction classification and confusion matrix metrics.ResultsThe cohort had a male predominance (53.8%), median age of 8.0 years (IQR 1.9−14.6), 21.0% incidence of acute kidney injury, and 2.3% mortality. The overall accuracy of the model for predicting change of <50% or ≥50% was 68.1% (95% CI 67.6%−68.7%). The accuracy of classification improved substantially with higher creatinine values from 29.9% (CI 28.9%−31.0%) in pairs with an admission creatinine <0.3 mg/dl to 90.0–96.3% in pairs with an admission creatinine of ≥0.6 mg/dl. The model had a negative predictive value of 97.2% and a positive predictive value of 7.1%. The number needed to evaluate to detect one true change ≥50% was 14.Discussion24-hour creatinine change consistent with acute kidney injury can be predicted using routine clinical data in a machine learning model, indicating risk of significant renal dysfunction before it is measured clinically. Positive predictive performance is limited by clinical reliance on creatinine.
format Article
id doaj-art-1dbfc4b406444bff934c2d2d2e341a39
institution DOAJ
issn 2296-2360
language English
publishDate 2025-04-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Pediatrics
spelling doaj-art-1dbfc4b406444bff934c2d2d2e341a392025-08-20T03:04:30ZengFrontiers Media S.A.Frontiers in Pediatrics2296-23602025-04-011310.3389/fped.2025.15498361549836Development of a neural network model for early detection of creatinine change in critically Ill childrenCeleste G. DixonEduardo A. Trujillo RiveraAnita K. PatelMurray M. PollackIntroductionRenal dysfunction is common in critically ill children and increases morbidity and mortality risk. Diagnosis and management of renal dysfunction relies on creatinine, a delayed marker of renal injury. We aimed to develop and validate a machine learning model using routinely collected clinical data to predict 24-hour creatinine change in critically ill children before change is observed clinically.MethodsRetrospective cohort study of 39,932 pediatric intensive care unit encounters in a national multicenter database from 2007 to 2022. A neural network was trained to predict <50% or ≥50% creatinine change in the next 24 h. Admission demographics, routinely measured vital signs, laboratory tests, and medication use variables were used as predictors for the model. Data set was randomly split at the encounter level into model development (80%) and test (20%) sets. Performance and clinical relevance was assessed in the test set by accuracy of prediction classification and confusion matrix metrics.ResultsThe cohort had a male predominance (53.8%), median age of 8.0 years (IQR 1.9−14.6), 21.0% incidence of acute kidney injury, and 2.3% mortality. The overall accuracy of the model for predicting change of <50% or ≥50% was 68.1% (95% CI 67.6%−68.7%). The accuracy of classification improved substantially with higher creatinine values from 29.9% (CI 28.9%−31.0%) in pairs with an admission creatinine <0.3 mg/dl to 90.0–96.3% in pairs with an admission creatinine of ≥0.6 mg/dl. The model had a negative predictive value of 97.2% and a positive predictive value of 7.1%. The number needed to evaluate to detect one true change ≥50% was 14.Discussion24-hour creatinine change consistent with acute kidney injury can be predicted using routine clinical data in a machine learning model, indicating risk of significant renal dysfunction before it is measured clinically. Positive predictive performance is limited by clinical reliance on creatinine.https://www.frontiersin.org/articles/10.3389/fped.2025.1549836/fullacute kidney injurycreatininepediatric intensive care unitmachine learningneural network model
spellingShingle Celeste G. Dixon
Eduardo A. Trujillo Rivera
Anita K. Patel
Murray M. Pollack
Development of a neural network model for early detection of creatinine change in critically Ill children
Frontiers in Pediatrics
acute kidney injury
creatinine
pediatric intensive care unit
machine learning
neural network model
title Development of a neural network model for early detection of creatinine change in critically Ill children
title_full Development of a neural network model for early detection of creatinine change in critically Ill children
title_fullStr Development of a neural network model for early detection of creatinine change in critically Ill children
title_full_unstemmed Development of a neural network model for early detection of creatinine change in critically Ill children
title_short Development of a neural network model for early detection of creatinine change in critically Ill children
title_sort development of a neural network model for early detection of creatinine change in critically ill children
topic acute kidney injury
creatinine
pediatric intensive care unit
machine learning
neural network model
url https://www.frontiersin.org/articles/10.3389/fped.2025.1549836/full
work_keys_str_mv AT celestegdixon developmentofaneuralnetworkmodelforearlydetectionofcreatininechangeincriticallyillchildren
AT eduardoatrujillorivera developmentofaneuralnetworkmodelforearlydetectionofcreatininechangeincriticallyillchildren
AT anitakpatel developmentofaneuralnetworkmodelforearlydetectionofcreatininechangeincriticallyillchildren
AT murraympollack developmentofaneuralnetworkmodelforearlydetectionofcreatininechangeincriticallyillchildren