Objectives: This study aims to improve early detection of cardiac surgery-associated acute kidney injury using artificial intelligence-based algorithms.
Methods: Data from consecutive patients undergoing cardiac surgery between 2008 and 2018 in our institution served as the source for artificial intelligence-based modeling. Cardiac surgery-associated acute kidney injury was defined according to the Kidney Disease Improving Global Outcomes criteria. Different machine learning algorithms were trained and validated to detect cardiac surgery-associated acute kidney injury within 12 hours after surgery. Demographic characteristics, comorbidities, preoperative cardiac status, intra- and postoperative variables including creatinine and hemoglobin values were retrieved for analysis.
Results: From 7507 patients analyzed, 1699 patients (22.6 %) developed cardiac surgery-associated acute kidney injury. The ultimate detection model, 'Detect-A(K)I', recognizes cardiac surgery-associated acute kidney injury within 12 hours with an area under the curve of 88.0 %, sensitivity of 78.0 %, specificity of 78.9 %, and accuracy of 82.1 %. The optimal parameter set includes serial changes of creatinine and hemoglobin, operative emergency, bleeding-associated variables, cardiac ischemic time and cardiac function-associated variables, age, diuretics and active infection, chronic obstructive lung and peripheral vascular disease.
Conclusion: The 'Detect-A(K)I' model successfully detects cardiac surgery-associated acute kidney injury within 12 hours after surgery with the best discriminatory characteristics reported so far.
%0 Journal Article
%1 kalisnik2022artificial
%A Kalisnik, Jurij Matija
%A Bauer, André
%A Vogt, Ferdinand Aurel
%A Stickl, Franziska Josephine
%A Zibert, Janez
%A Fittkau, Matthias
%A Bertsch, Thomas
%A Kounev, Samuel
%A Fischlein, Theodor
%D 2022
%J European Journal of Cardio-Thoracic Surgery
%K csa-aki descartes t_interdisciplinary t_journalmagazine
%T Artificial Intelligence-Based Early Detection Of Acute Kidney Injury After Cardiac Surgery
%X Objectives: This study aims to improve early detection of cardiac surgery-associated acute kidney injury using artificial intelligence-based algorithms.
Methods: Data from consecutive patients undergoing cardiac surgery between 2008 and 2018 in our institution served as the source for artificial intelligence-based modeling. Cardiac surgery-associated acute kidney injury was defined according to the Kidney Disease Improving Global Outcomes criteria. Different machine learning algorithms were trained and validated to detect cardiac surgery-associated acute kidney injury within 12 hours after surgery. Demographic characteristics, comorbidities, preoperative cardiac status, intra- and postoperative variables including creatinine and hemoglobin values were retrieved for analysis.
Results: From 7507 patients analyzed, 1699 patients (22.6 %) developed cardiac surgery-associated acute kidney injury. The ultimate detection model, 'Detect-A(K)I', recognizes cardiac surgery-associated acute kidney injury within 12 hours with an area under the curve of 88.0 %, sensitivity of 78.0 %, specificity of 78.9 %, and accuracy of 82.1 %. The optimal parameter set includes serial changes of creatinine and hemoglobin, operative emergency, bleeding-associated variables, cardiac ischemic time and cardiac function-associated variables, age, diuretics and active infection, chronic obstructive lung and peripheral vascular disease.
Conclusion: The 'Detect-A(K)I' model successfully detects cardiac surgery-associated acute kidney injury within 12 hours after surgery with the best discriminatory characteristics reported so far.
@article{kalisnik2022artificial,
abstract = {Objectives: This study aims to improve early detection of cardiac surgery-associated acute kidney injury using artificial intelligence-based algorithms.
Methods: Data from consecutive patients undergoing cardiac surgery between 2008 and 2018 in our institution served as the source for artificial intelligence-based modeling. Cardiac surgery-associated acute kidney injury was defined according to the Kidney Disease Improving Global Outcomes criteria. Different machine learning algorithms were trained and validated to detect cardiac surgery-associated acute kidney injury within 12 hours after surgery. Demographic characteristics, comorbidities, preoperative cardiac status, intra- and postoperative variables including creatinine and hemoglobin values were retrieved for analysis.
Results: From 7507 patients analyzed, 1699 patients (22.6 %) developed cardiac surgery-associated acute kidney injury. The ultimate detection model, 'Detect-A(K)I', recognizes cardiac surgery-associated acute kidney injury within 12 hours with an area under the curve of 88.0 %, sensitivity of 78.0 %, specificity of 78.9 %, and accuracy of 82.1 %. The optimal parameter set includes serial changes of creatinine and hemoglobin, operative emergency, bleeding-associated variables, cardiac ischemic time and cardiac function-associated variables, age, diuretics and active infection, chronic obstructive lung and peripheral vascular disease.
Conclusion: The 'Detect-A(K)I' model successfully detects cardiac surgery-associated acute kidney injury within 12 hours after surgery with the best discriminatory characteristics reported so far.
},
added-at = {2024-05-04T01:06:17.000+0200},
author = {Kalisnik, Jurij Matija and Bauer, Andr{é} and Vogt, Ferdinand Aurel and Stickl, Franziska Josephine and Zibert, Janez and Fittkau, Matthias and Bertsch, Thomas and Kounev, Samuel and Fischlein, Theodor},
biburl = {https://www.bibsonomy.org/bibtex/2a374a31381d57f83372405b6aa0b813c/se-group},
interhash = {f62bcaa35f30e0a17fbd0e3451ad5ecf},
intrahash = {a374a31381d57f83372405b6aa0b813c},
journal = {European Journal of Cardio-Thoracic Surgery},
keywords = {csa-aki descartes t_interdisciplinary t_journalmagazine},
note = {Joint first authorship; To be published soon},
timestamp = {2024-05-04T01:06:17.000+0200},
title = {Artificial Intelligence-Based Early Detection Of Acute Kidney Injury After Cardiac Surgery},
year = 2022
}