Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set

Abstract During the perioperative period patients often suffer complications, including acute kidney injury (AKI), reintubation, and mortality. In order to effectively prevent these complications, high-risk patients must be readily identified. However, most current risk scores are designed to predic...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Ira S. Hofer, Christine Lee, Eilon Gabel, Pierre Baldi, Maxime Cannesson
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2020
Materias:
Acceso en línea:https://doaj.org/article/9361958a0ed84b9b8b3995be232455af
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:9361958a0ed84b9b8b3995be232455af
record_format dspace
spelling oai:doaj.org-article:9361958a0ed84b9b8b3995be232455af2021-12-02T18:27:51ZDevelopment and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set10.1038/s41746-020-0248-02398-6352https://doaj.org/article/9361958a0ed84b9b8b3995be232455af2020-04-01T00:00:00Zhttps://doi.org/10.1038/s41746-020-0248-0https://doaj.org/toc/2398-6352Abstract During the perioperative period patients often suffer complications, including acute kidney injury (AKI), reintubation, and mortality. In order to effectively prevent these complications, high-risk patients must be readily identified. However, most current risk scores are designed to predict a single postoperative complication and often lack specificity on the patient level. In other fields, machine learning (ML) has been shown to successfully create models to predict multiple end points using a single input feature set. We hypothesized that ML can be used to create models to predict postoperative mortality, AKI, reintubation, and a combined outcome using a single set of features available at the end of surgery. A set of 46 features available at the end of surgery, including drug dosing, blood loss, vital signs, and others were extracted. Additionally, six additional features accounting for total intraoperative hypotension were extracted and trialed for different models. A total of 59,981 surgical procedures met inclusion criteria and the deep neural networks (DNN) were trained on 80% of the data, with 20% reserved for testing. The network performances were then compared to ASA Physical Status. In addition to creating separate models for each outcome, a multitask learning model was trialed that used information on all outcomes to predict the likelihood of each outcome individually. The overall rate of the examined complications in this data set was 0.79% for mortality, 22.3% (of 21,676 patients with creatinine values) for AKI, and 1.1% for reintubation. Overall, there was significant overlap between the various model types for each outcome, with no one modeling technique consistently performing the best. However, the best DNN models did beat the ASA score for all outcomes other than mortality. The highest area under the receiver operating characteristic curve (AUC) models were 0.792 (0.775–0.808) for AKI, 0.879 (0.851–0.905) for reintubation, 0.907 (0.872–0.938) for mortality, and 0.874 (0.864–0.866) for any outcome. The ASA score alone achieved AUCs of 0.652 (0.636–0.669) for AKI, 0.787 (0.757–0.818) for reintubation, 0.839 (0.804–0.875) for mortality, and 0.76 (0.748–0.773) for any outcome. Overall, the DNN architecture was able to create models that outperformed the ASA physical status to predict all outcomes based on a single feature set, consisting of objective data available at the end of surgery. No one model architecture consistently performed the best.Ira S. HoferChristine LeeEilon GabelPierre BaldiMaxime CannessonNature PortfolioarticleComputer applications to medicine. Medical informaticsR858-859.7ENnpj Digital Medicine, Vol 3, Iss 1, Pp 1-10 (2020)
institution DOAJ
collection DOAJ
language EN
topic Computer applications to medicine. Medical informatics
R858-859.7
spellingShingle Computer applications to medicine. Medical informatics
R858-859.7
Ira S. Hofer
Christine Lee
Eilon Gabel
Pierre Baldi
Maxime Cannesson
Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
description Abstract During the perioperative period patients often suffer complications, including acute kidney injury (AKI), reintubation, and mortality. In order to effectively prevent these complications, high-risk patients must be readily identified. However, most current risk scores are designed to predict a single postoperative complication and often lack specificity on the patient level. In other fields, machine learning (ML) has been shown to successfully create models to predict multiple end points using a single input feature set. We hypothesized that ML can be used to create models to predict postoperative mortality, AKI, reintubation, and a combined outcome using a single set of features available at the end of surgery. A set of 46 features available at the end of surgery, including drug dosing, blood loss, vital signs, and others were extracted. Additionally, six additional features accounting for total intraoperative hypotension were extracted and trialed for different models. A total of 59,981 surgical procedures met inclusion criteria and the deep neural networks (DNN) were trained on 80% of the data, with 20% reserved for testing. The network performances were then compared to ASA Physical Status. In addition to creating separate models for each outcome, a multitask learning model was trialed that used information on all outcomes to predict the likelihood of each outcome individually. The overall rate of the examined complications in this data set was 0.79% for mortality, 22.3% (of 21,676 patients with creatinine values) for AKI, and 1.1% for reintubation. Overall, there was significant overlap between the various model types for each outcome, with no one modeling technique consistently performing the best. However, the best DNN models did beat the ASA score for all outcomes other than mortality. The highest area under the receiver operating characteristic curve (AUC) models were 0.792 (0.775–0.808) for AKI, 0.879 (0.851–0.905) for reintubation, 0.907 (0.872–0.938) for mortality, and 0.874 (0.864–0.866) for any outcome. The ASA score alone achieved AUCs of 0.652 (0.636–0.669) for AKI, 0.787 (0.757–0.818) for reintubation, 0.839 (0.804–0.875) for mortality, and 0.76 (0.748–0.773) for any outcome. Overall, the DNN architecture was able to create models that outperformed the ASA physical status to predict all outcomes based on a single feature set, consisting of objective data available at the end of surgery. No one model architecture consistently performed the best.
format article
author Ira S. Hofer
Christine Lee
Eilon Gabel
Pierre Baldi
Maxime Cannesson
author_facet Ira S. Hofer
Christine Lee
Eilon Gabel
Pierre Baldi
Maxime Cannesson
author_sort Ira S. Hofer
title Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
title_short Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
title_full Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
title_fullStr Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
title_full_unstemmed Development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
title_sort development and validation of a deep neural network model to predict postoperative mortality, acute kidney injury, and reintubation using a single feature set
publisher Nature Portfolio
publishDate 2020
url https://doaj.org/article/9361958a0ed84b9b8b3995be232455af
work_keys_str_mv AT irashofer developmentandvalidationofadeepneuralnetworkmodeltopredictpostoperativemortalityacutekidneyinjuryandreintubationusingasinglefeatureset
AT christinelee developmentandvalidationofadeepneuralnetworkmodeltopredictpostoperativemortalityacutekidneyinjuryandreintubationusingasinglefeatureset
AT eilongabel developmentandvalidationofadeepneuralnetworkmodeltopredictpostoperativemortalityacutekidneyinjuryandreintubationusingasinglefeatureset
AT pierrebaldi developmentandvalidationofadeepneuralnetworkmodeltopredictpostoperativemortalityacutekidneyinjuryandreintubationusingasinglefeatureset
AT maximecannesson developmentandvalidationofadeepneuralnetworkmodeltopredictpostoperativemortalityacutekidneyinjuryandreintubationusingasinglefeatureset
_version_ 1718377993148039168