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 · 2025
DOI: 10.1371/journal.pone.0326124 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Lorenzo Ruinelli und 5 weiteren Autor:innen. Beteiligte Einrichtung: Area ICT, Ente Ospedaliero Cantonale, Bellinzona, Switzerland. Hauptthemen laut MEDLINE: Acute Kidney Injury, Electronic Health Records, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background
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.
Methods
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.
Findings
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.
Interpretation
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.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Area ICT, Ente Ospedaliero Cantonale, Bellinzona, Switzerland.
- Clinical Trial Unit, Ente Ospedaliero Cantonale, Bellinzona, Switzerland.
- Division of Nephrology, Ente Ospedaliero Cantonale, Lugano, Switzerland.
- Faculty of Biomedical Sciences, Università della Svizzera italiana, Lugano, Switzerland.
- Department of Medicine, Ente Ospedaliero Cantonale, Bellinzona, Switzerland.
- Clinical School, University of New South Wales, Sydney, Australia.
ORCID-Profile: Lorenzo Ruinelli, Antonio Bellasi
Zitieren
APA
Ruinelli, L., Cippà, P., Sieber, C., Di Serio, C., Ferrari, P., & Bellasi, A. (2025). 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. https://doi.org/10.1371/journal.pone.0326124
Vancouver
Ruinelli L, Cippà P, Sieber C, Di Serio C, Ferrari P, Bellasi A. 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. 2025. doi:10.1371/journal.pone.0326124
BibTeX
@article{Ruinelli2025,
author = {Ruinelli, Lorenzo and Cippà, Pietro and Sieber, Chantal and Di Serio, Clelia and Ferrari, Paolo and Bellasi, Antonio},
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},
journal = {PLOS One},
year = {2025},
doi = {10.1371/journal.pone.0326124}
}
EUVIMED