Cargando…

Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors

Acute kidney injury (AKI) is a major postoperative complication that lacks established intraoperative predictors. Our objective was to develop a prediction model using preoperative and high-frequency intraoperative data for postoperative AKI. In this retrospective cohort study, we evaluated 77,428 o...

Descripción completa

Detalles Bibliográficos
Autores principales: Zamirpour, Siavash, Hubbard, Alan E., Feng, Jean, Butte, Atul J., Pirracchio, Romain, Bishara, Andrew
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451203/
https://www.ncbi.nlm.nih.gov/pubmed/37627817
http://dx.doi.org/10.3390/bioengineering10080932
_version_ 1785095379838042112
author Zamirpour, Siavash
Hubbard, Alan E.
Feng, Jean
Butte, Atul J.
Pirracchio, Romain
Bishara, Andrew
author_facet Zamirpour, Siavash
Hubbard, Alan E.
Feng, Jean
Butte, Atul J.
Pirracchio, Romain
Bishara, Andrew
author_sort Zamirpour, Siavash
collection PubMed
description Acute kidney injury (AKI) is a major postoperative complication that lacks established intraoperative predictors. Our objective was to develop a prediction model using preoperative and high-frequency intraoperative data for postoperative AKI. In this retrospective cohort study, we evaluated 77,428 operative cases at a single academic center between 2016 and 2022. A total of 11,212 cases with serum creatinine (sCr) data were included in the analysis. Then, 8519 cases were randomly assigned to the training set and the remainder to the validation set. Fourteen preoperative and twenty intraoperative variables were evaluated using elastic net followed by hierarchical group least absolute shrinkage and selection operator (LASSO) regression. The training set was 56% male and had a median [IQR] age of 62 (51–72) and a 6% AKI rate. Retained model variables were preoperative sCr values, the number of minutes meeting cutoffs for urine output, heart rate, perfusion index intraoperatively, and the total estimated blood loss. The area under the receiver operator characteristic curve was 0.81 (95% CI, 0.77–0.85). At a score threshold of 0.767, specificity was 77% and sensitivity was 74%. A web application that calculates the model score is available online. Our findings demonstrate the utility of intraoperative time series data for prediction problems, including a new potential use of the perfusion index. Further research is needed to evaluate the model in clinical settings.
format Online
Article
Text
id pubmed-10451203
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-104512032023-08-26 Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors Zamirpour, Siavash Hubbard, Alan E. Feng, Jean Butte, Atul J. Pirracchio, Romain Bishara, Andrew Bioengineering (Basel) Article Acute kidney injury (AKI) is a major postoperative complication that lacks established intraoperative predictors. Our objective was to develop a prediction model using preoperative and high-frequency intraoperative data for postoperative AKI. In this retrospective cohort study, we evaluated 77,428 operative cases at a single academic center between 2016 and 2022. A total of 11,212 cases with serum creatinine (sCr) data were included in the analysis. Then, 8519 cases were randomly assigned to the training set and the remainder to the validation set. Fourteen preoperative and twenty intraoperative variables were evaluated using elastic net followed by hierarchical group least absolute shrinkage and selection operator (LASSO) regression. The training set was 56% male and had a median [IQR] age of 62 (51–72) and a 6% AKI rate. Retained model variables were preoperative sCr values, the number of minutes meeting cutoffs for urine output, heart rate, perfusion index intraoperatively, and the total estimated blood loss. The area under the receiver operator characteristic curve was 0.81 (95% CI, 0.77–0.85). At a score threshold of 0.767, specificity was 77% and sensitivity was 74%. A web application that calculates the model score is available online. Our findings demonstrate the utility of intraoperative time series data for prediction problems, including a new potential use of the perfusion index. Further research is needed to evaluate the model in clinical settings. MDPI 2023-08-05 /pmc/articles/PMC10451203/ /pubmed/37627817 http://dx.doi.org/10.3390/bioengineering10080932 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zamirpour, Siavash
Hubbard, Alan E.
Feng, Jean
Butte, Atul J.
Pirracchio, Romain
Bishara, Andrew
Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors
title Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors
title_full Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors
title_fullStr Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors
title_full_unstemmed Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors
title_short Development of a Machine Learning Model of Postoperative Acute Kidney Injury Using Non-Invasive Time-Sensitive Intraoperative Predictors
title_sort development of a machine learning model of postoperative acute kidney injury using non-invasive time-sensitive intraoperative predictors
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10451203/
https://www.ncbi.nlm.nih.gov/pubmed/37627817
http://dx.doi.org/10.3390/bioengineering10080932
work_keys_str_mv AT zamirpoursiavash developmentofamachinelearningmodelofpostoperativeacutekidneyinjuryusingnoninvasivetimesensitiveintraoperativepredictors
AT hubbardalane developmentofamachinelearningmodelofpostoperativeacutekidneyinjuryusingnoninvasivetimesensitiveintraoperativepredictors
AT fengjean developmentofamachinelearningmodelofpostoperativeacutekidneyinjuryusingnoninvasivetimesensitiveintraoperativepredictors
AT butteatulj developmentofamachinelearningmodelofpostoperativeacutekidneyinjuryusingnoninvasivetimesensitiveintraoperativepredictors
AT pirracchioromain developmentofamachinelearningmodelofpostoperativeacutekidneyinjuryusingnoninvasivetimesensitiveintraoperativepredictors
AT bisharaandrew developmentofamachinelearningmodelofpostoperativeacutekidneyinjuryusingnoninvasivetimesensitiveintraoperativepredictors