Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.

<h4>Background</h4>Acute kidney injury (AKI) and acute kidney disease (AKD) are frequent complications of hospitalization, resulting in reduced outcomes and increased cost burden. However, these conditions are only sometimes recognized and promptly treated. Leveraging electronic health r...

Full description

Saved in:
Bibliographic Details
Main Authors: Lorenzo Ruinelli, Pietro Cippà, Chantal Sieber, Clelia Di Serio, Paolo Ferrari, Antonio Bellasi
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0326124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850116518482804736
author Lorenzo Ruinelli
Pietro Cippà
Chantal Sieber
Clelia Di Serio
Paolo Ferrari
Antonio Bellasi
author_facet Lorenzo Ruinelli
Pietro Cippà
Chantal Sieber
Clelia Di Serio
Paolo Ferrari
Antonio Bellasi
author_sort Lorenzo Ruinelli
collection DOAJ
description <h4>Background</h4>Acute kidney injury (AKI) and acute kidney disease (AKD) are frequent complications of hospitalization, resulting in reduced outcomes and increased cost burden. However, these conditions are only sometimes recognized and promptly treated. Leveraging electronic health records (EHR), we explored the potential of artificial intelligence (AI) in diagnosing AKI and AKD during hospitalization.<h4>Methods</h4>We retrospectively analyzed EHRs collected from all patients admitted in 2022 to our public hospital network. AKI and AKD were defined according to international guidelines. The database was divided into training and validation sets. Machine Learning (ML) algorithms were developed with 10-fold cross-validation, and diagnostic accuracy was evaluated.<h4>Findings</h4>We analyzed 34,579 hospitalizations (mean age of 60 years, 50% females). Baseline renal function was available in ~50% of cases. AKI and AKD complicated 10% and 1.5% of hospitalizations, respectively. The majority of AKI episodes (77%) occurred within the first three days of hospitalization, and >50% of subjects with AKI were discharged before complete renal function recovery. ML accurately predicted AKI (AUC-ROC 79%) during hospitalization, based on data available before and at hospital admission. Among subjects with AKI on the first day and longer in-hospital observation, the ML accuracy in predicting AKD transition increased (AUC-ROC from 76% to 88%) by integrating EHR accumulated during the hospitalization. The negative predictive value (NPV) progressively increased from 94% to 98% consistently. Shapely additive explanations documented that age, urgent hospital admission, AKI severity, and baseline renal function were associated with AKI. Renal function trajectory during the first days of hospitalization was the most relevant predictor of AKD.<h4>Interpretation</h4>ML, relying on EHR before and during hospitalization, may accurately predict AKI and AKD. The high NPV also suggests its implementation as a tool to rule out the risk of renal failure, aid in individualizing patient care, and allocate healthcare resources.
format Article
id doaj-art-0abfe68fc54c4369b93ddf46e1fcc531
institution OA Journals
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-0abfe68fc54c4369b93ddf46e1fcc5312025-08-20T02:36:18ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01207e032612410.1371/journal.pone.0326124Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.Lorenzo RuinelliPietro CippàChantal SieberClelia Di SerioPaolo FerrariAntonio Bellasi<h4>Background</h4>Acute kidney injury (AKI) and acute kidney disease (AKD) are frequent complications of hospitalization, resulting in reduced outcomes and increased cost burden. However, these conditions are only sometimes recognized and promptly treated. Leveraging electronic health records (EHR), we explored the potential of artificial intelligence (AI) in diagnosing AKI and AKD during hospitalization.<h4>Methods</h4>We retrospectively analyzed EHRs collected from all patients admitted in 2022 to our public hospital network. AKI and AKD were defined according to international guidelines. The database was divided into training and validation sets. Machine Learning (ML) algorithms were developed with 10-fold cross-validation, and diagnostic accuracy was evaluated.<h4>Findings</h4>We analyzed 34,579 hospitalizations (mean age of 60 years, 50% females). Baseline renal function was available in ~50% of cases. AKI and AKD complicated 10% and 1.5% of hospitalizations, respectively. The majority of AKI episodes (77%) occurred within the first three days of hospitalization, and >50% of subjects with AKI were discharged before complete renal function recovery. ML accurately predicted AKI (AUC-ROC 79%) during hospitalization, based on data available before and at hospital admission. Among subjects with AKI on the first day and longer in-hospital observation, the ML accuracy in predicting AKD transition increased (AUC-ROC from 76% to 88%) by integrating EHR accumulated during the hospitalization. The negative predictive value (NPV) progressively increased from 94% to 98% consistently. Shapely additive explanations documented that age, urgent hospital admission, AKI severity, and baseline renal function were associated with AKI. Renal function trajectory during the first days of hospitalization was the most relevant predictor of AKD.<h4>Interpretation</h4>ML, relying on EHR before and during hospitalization, may accurately predict AKI and AKD. The high NPV also suggests its implementation as a tool to rule out the risk of renal failure, aid in individualizing patient care, and allocate healthcare resources.https://doi.org/10.1371/journal.pone.0326124
spellingShingle Lorenzo Ruinelli
Pietro Cippà
Chantal Sieber
Clelia Di Serio
Paolo Ferrari
Antonio Bellasi
Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.
PLoS ONE
title Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.
title_full Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.
title_fullStr Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.
title_full_unstemmed Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.
title_short Usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease: A proof of concept study.
title_sort usability of machine learning algorithms based on electronic health records for the prediction of acute kidney injury and transition to acute kidney disease a proof of concept study
url https://doi.org/10.1371/journal.pone.0326124
work_keys_str_mv AT lorenzoruinelli usabilityofmachinelearningalgorithmsbasedonelectronichealthrecordsforthepredictionofacutekidneyinjuryandtransitiontoacutekidneydiseaseaproofofconceptstudy
AT pietrocippa usabilityofmachinelearningalgorithmsbasedonelectronichealthrecordsforthepredictionofacutekidneyinjuryandtransitiontoacutekidneydiseaseaproofofconceptstudy
AT chantalsieber usabilityofmachinelearningalgorithmsbasedonelectronichealthrecordsforthepredictionofacutekidneyinjuryandtransitiontoacutekidneydiseaseaproofofconceptstudy
AT cleliadiserio usabilityofmachinelearningalgorithmsbasedonelectronichealthrecordsforthepredictionofacutekidneyinjuryandtransitiontoacutekidneydiseaseaproofofconceptstudy
AT paoloferrari usabilityofmachinelearningalgorithmsbasedonelectronichealthrecordsforthepredictionofacutekidneyinjuryandtransitiontoacutekidneydiseaseaproofofconceptstudy
AT antoniobellasi usabilityofmachinelearningalgorithmsbasedonelectronichealthrecordsforthepredictionofacutekidneyinjuryandtransitiontoacutekidneydiseaseaproofofconceptstudy