Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database

Michael Fujarski; Christian Porschen; Lucas Plagwitz; Alexander Brenner; Narges Ghoreishi; Patrick Thoral; Harm-Jan de Grooth; Paul Elbers; Raphael Weiss; Melanie Meersch; Alexander Zarbock; Thilo Caspar von Groote; Julian Varghese

doi:10.3233/SHTI220419

Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database

Michael Fujarski, Christian Porschen, Lucas Plagwitz, Alexander Brenner, Narges Ghoreishi, Patrick Thoral, Harm-Jan de Grooth, Paul Elbers, Raphael Weiss, Melanie Meersch, Alexander Zarbock, Thilo Caspar von Groote, Julian Varghese

Research output: Contribution to journal › Article › Academic › peer-review

Abstract

Acute kidney injury (AKI) is a common complication in critically ill patients and is associated with long-term complications and an increased mortality. This work presents preliminary findings from the first freely available European intensive care database released by Amsterdam UMC. A machine learning (ML) model was developed to predict AKI in the intensive care unit 12 hours before the actual event. Main features of the model included medications and hemodynamic parameters. Our models perform with an accuracy of 81.8% on moderate to severe AKI and 79.8% on all AKI patients. Those results can compete with models reported in the literature and introduce an ML model for AKI based on European patient data.

Original language	English
Pages (from-to)	139-140
Number of pages	2
Journal	Studies in Health Technology and Informatics
Volume	294
DOIs	https://doi.org/10.3233/SHTI220419
Publication status	Published - 25 May 2022
Externally published	Yes

Keywords

Access to Information
Acute Kidney Injury/diagnosis
Critical Illness
Databases, Factual
Humans
Intensive Care Units

Access to Document

10.3233/SHTI220419Licence: CC BY-NC

Cite this

Fujarski, M., Porschen, C., Plagwitz, L., Brenner, A., Ghoreishi, N., Thoral, P., de Grooth, H.-J., Elbers, P., Weiss, R., Meersch, M., Zarbock, A., von Groote, T. C., & Varghese, J. (2022). Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database. Studies in Health Technology and Informatics, 294, 139-140. https://doi.org/10.3233/SHTI220419

@article{08e4382bb216442fa9a18e366b9028cf,

title = "Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database",

abstract = "Acute kidney injury (AKI) is a common complication in critically ill patients and is associated with long-term complications and an increased mortality. This work presents preliminary findings from the first freely available European intensive care database released by Amsterdam UMC. A machine learning (ML) model was developed to predict AKI in the intensive care unit 12 hours before the actual event. Main features of the model included medications and hemodynamic parameters. Our models perform with an accuracy of 81.8% on moderate to severe AKI and 79.8% on all AKI patients. Those results can compete with models reported in the literature and introduce an ML model for AKI based on European patient data.",

keywords = "Access to Information, Acute Kidney Injury/diagnosis, Critical Illness, Databases, Factual, Humans, Intensive Care Units",

author = "Michael Fujarski and Christian Porschen and Lucas Plagwitz and Alexander Brenner and Narges Ghoreishi and Patrick Thoral and {de Grooth}, Harm-Jan and Paul Elbers and Raphael Weiss and Melanie Meersch and Alexander Zarbock and {von Groote}, {Thilo Caspar} and Julian Varghese",

note = "Publisher Copyright: {\textcopyright} 2022 European Federation for Medical Informatics (EFMI) and IOS Press.",

year = "2022",

month = may,

day = "25",

doi = "10.3233/SHTI220419",

language = "English",

volume = "294",

pages = "139--140",

journal = "Studies in Health Technology and Informatics",

issn = "0926-9630",

publisher = "IOS Press",

}

Fujarski, M, Porschen, C, Plagwitz, L, Brenner, A, Ghoreishi, N, Thoral, P, de Grooth, H-J, Elbers, P, Weiss, R, Meersch, M, Zarbock, A, von Groote, TC & Varghese, J 2022, 'Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database', Studies in Health Technology and Informatics, vol. 294, pp. 139-140. https://doi.org/10.3233/SHTI220419

TY - JOUR

T1 - Prediction of Acute Kidney Injury in the Intensive Care Unit

T2 - Preliminary Findings in a European Open Access Database

AU - Fujarski, Michael

AU - Porschen, Christian

AU - Plagwitz, Lucas

AU - Brenner, Alexander

AU - Ghoreishi, Narges

AU - Thoral, Patrick

AU - de Grooth, Harm-Jan

AU - Elbers, Paul

AU - Weiss, Raphael

AU - Meersch, Melanie

AU - Zarbock, Alexander

AU - von Groote, Thilo Caspar

AU - Varghese, Julian

PY - 2022/5/25

Y1 - 2022/5/25

N2 - Acute kidney injury (AKI) is a common complication in critically ill patients and is associated with long-term complications and an increased mortality. This work presents preliminary findings from the first freely available European intensive care database released by Amsterdam UMC. A machine learning (ML) model was developed to predict AKI in the intensive care unit 12 hours before the actual event. Main features of the model included medications and hemodynamic parameters. Our models perform with an accuracy of 81.8% on moderate to severe AKI and 79.8% on all AKI patients. Those results can compete with models reported in the literature and introduce an ML model for AKI based on European patient data.

AB - Acute kidney injury (AKI) is a common complication in critically ill patients and is associated with long-term complications and an increased mortality. This work presents preliminary findings from the first freely available European intensive care database released by Amsterdam UMC. A machine learning (ML) model was developed to predict AKI in the intensive care unit 12 hours before the actual event. Main features of the model included medications and hemodynamic parameters. Our models perform with an accuracy of 81.8% on moderate to severe AKI and 79.8% on all AKI patients. Those results can compete with models reported in the literature and introduce an ML model for AKI based on European patient data.

KW - Access to Information

KW - Acute Kidney Injury/diagnosis

KW - Critical Illness

KW - Databases, Factual

KW - Humans

KW - Intensive Care Units

U2 - 10.3233/SHTI220419

DO - 10.3233/SHTI220419

M3 - Article

C2 - 35612039

SN - 0926-9630

VL - 294

SP - 139

EP - 140

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

ER -

Prediction of Acute Kidney Injury in the Intensive Care Unit: Preliminary Findings in a European Open Access Database

Abstract

Keywords

Access to Document

Fingerprint

Cite this