Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients

Nafiseh Mollaei; Ana Rita Londral; Catia Cepeda; Salomé Azevedo; Jorge Pinheiro Santos; Pedro Coelho; José Fragata; Hugo Gamboa

doi:10.1109/ICBSII51839.2021.9445145

Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients

Nafiseh Mollaei, Ana Rita Londral, Catia Cepeda, Salomé Azevedo, Jorge Pinheiro Santos, Pedro Coelho, José Fragata, Hugo Gamboa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

The goal of this study was to apply machine learning (ML) methods to predict the Length of Stay in an Intensive Care Unit (LOS-ICU) based on preoperative factors. To optimize the capacity of the ICU in surgery department, the prediction of a long stay (more than 2 days) can support the clinical decision making on accepting or delaying a patient intervention, considering the ICU occupancy. A database with records from 7364 patients that were operated in the Cardiothoracic surgery department of a public Portuguese hospital was used as the base of ML algorithms training. Regarding the risk of the patients to be in the group of long LOS-ICU, we compared five machine learning algorithms including Gradient Boosting, Random Forest, Support Vector Machine (SVM), Adaboost and Logistic Regression. We studied the classifier performance to adjust the sensitivity of a long stay classification, in order to reduce the potential of long LOS-ICU classification being miss classified as a short LOS-ICU.

Original language	English
Title of host publication	Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)	9781665441261
DOIs	https://doi.org/10.1109/ICBSII51839.2021.9445145
Publication status	Published - 25 Mar 2021
Event	7th IEEE International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021 - Chennai, India Duration: 25 Mar 2021 → 27 Mar 2021

Conference

Conference	7th IEEE International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021
Country/Territory	India
City	Chennai
Period	25/03/21 → 27/03/21

Keywords

Cardiac surgery
Classifier tuning
Machine learning
Preoperative risk factor

Access to Document

10.1109/ICBSII51839.2021.9445145

Cite this

Mollaei, N., Londral, A. R., Cepeda, C., Azevedo, S., Santos, J. P., Coelho, P., Fragata, J., & Gamboa, H. (2021). Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients. In Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021 Article 9445145 Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/ICBSII51839.2021.9445145

@inproceedings{3f82198679e24ec196c059a24e8a28ef,

title = "Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients",

abstract = "The goal of this study was to apply machine learning (ML) methods to predict the Length of Stay in an Intensive Care Unit (LOS-ICU) based on preoperative factors. To optimize the capacity of the ICU in surgery department, the prediction of a long stay (more than 2 days) can support the clinical decision making on accepting or delaying a patient intervention, considering the ICU occupancy. A database with records from 7364 patients that were operated in the Cardiothoracic surgery department of a public Portuguese hospital was used as the base of ML algorithms training. Regarding the risk of the patients to be in the group of long LOS-ICU, we compared five machine learning algorithms including Gradient Boosting, Random Forest, Support Vector Machine (SVM), Adaboost and Logistic Regression. We studied the classifier performance to adjust the sensitivity of a long stay classification, in order to reduce the potential of long LOS-ICU classification being miss classified as a short LOS-ICU. ",

keywords = "Cardiac surgery, Classifier tuning, Machine learning, Preoperative risk factor",

author = "Nafiseh Mollaei and Londral, {Ana Rita} and Catia Cepeda and Salom{\'e} Azevedo and Santos, {Jorge Pinheiro} and Pedro Coelho and Jos{\'e} Fragata and Hugo Gamboa",

note = "Funding Information: info:eu-repo/grantAgreement/FCT/OE/PD%2FBDE%2F142973%2F2018/PT# Publisher Copyright: {\textcopyright} 2021 IEEE. Copyright: Copyright 2021 Elsevier B.V., All rights reserved.; 7th IEEE International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021 ; Conference date: 25-03-2021 Through 27-03-2021",

year = "2021",

month = mar,

day = "25",

doi = "10.1109/ICBSII51839.2021.9445145",

language = "English",

booktitle = "Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

}

Mollaei, N , Londral, AR , Cepeda, C , Azevedo, S , Santos, JP , Coelho, P , Fragata, J & Gamboa, H 2021, Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients. in Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021., 9445145, Institute of Electrical and Electronics Engineers (IEEE), 7th IEEE International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021, Chennai, India, 25/03/21. https://doi.org/10.1109/ICBSII51839.2021.9445145

Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients. / Mollaei, Nafiseh ; Londral, Ana Rita ; Cepeda, Catia et al.
Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021. Institute of Electrical and Electronics Engineers (IEEE), 2021. 9445145.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients

AU - Mollaei, Nafiseh

AU - Londral, Ana Rita

AU - Cepeda, Catia

AU - Azevedo, Salomé

AU - Santos, Jorge Pinheiro

AU - Coelho, Pedro

AU - Fragata, José

AU - Gamboa, Hugo

PY - 2021/3/25

Y1 - 2021/3/25

N2 - The goal of this study was to apply machine learning (ML) methods to predict the Length of Stay in an Intensive Care Unit (LOS-ICU) based on preoperative factors. To optimize the capacity of the ICU in surgery department, the prediction of a long stay (more than 2 days) can support the clinical decision making on accepting or delaying a patient intervention, considering the ICU occupancy. A database with records from 7364 patients that were operated in the Cardiothoracic surgery department of a public Portuguese hospital was used as the base of ML algorithms training. Regarding the risk of the patients to be in the group of long LOS-ICU, we compared five machine learning algorithms including Gradient Boosting, Random Forest, Support Vector Machine (SVM), Adaboost and Logistic Regression. We studied the classifier performance to adjust the sensitivity of a long stay classification, in order to reduce the potential of long LOS-ICU classification being miss classified as a short LOS-ICU.

AB - The goal of this study was to apply machine learning (ML) methods to predict the Length of Stay in an Intensive Care Unit (LOS-ICU) based on preoperative factors. To optimize the capacity of the ICU in surgery department, the prediction of a long stay (more than 2 days) can support the clinical decision making on accepting or delaying a patient intervention, considering the ICU occupancy. A database with records from 7364 patients that were operated in the Cardiothoracic surgery department of a public Portuguese hospital was used as the base of ML algorithms training. Regarding the risk of the patients to be in the group of long LOS-ICU, we compared five machine learning algorithms including Gradient Boosting, Random Forest, Support Vector Machine (SVM), Adaboost and Logistic Regression. We studied the classifier performance to adjust the sensitivity of a long stay classification, in order to reduce the potential of long LOS-ICU classification being miss classified as a short LOS-ICU.

KW - Cardiac surgery

KW - Classifier tuning

KW - Machine learning

KW - Preoperative risk factor

UR - http://www.scopus.com/inward/record.url?scp=85107980997&partnerID=8YFLogxK

U2 - 10.1109/ICBSII51839.2021.9445145

DO - 10.1109/ICBSII51839.2021.9445145

M3 - Conference contribution

AN - SCOPUS:85107980997

BT - Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021

PB - Institute of Electrical and Electronics Engineers (IEEE)

T2 - 7th IEEE International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021

Y2 - 25 March 2021 through 27 March 2021

ER -

Mollaei N , Londral AR , Cepeda C , Azevedo S , Santos JP , Coelho P et al. Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients. In Proceedings of 2021 IEEE 7th International Conference on Bio Signals, Images and Instrumentation, ICBSII 2021. Institute of Electrical and Electronics Engineers (IEEE). 2021. 9445145 doi: 10.1109/ICBSII51839.2021.9445145

Length of Stay Prediction in Acute Intensive Care Unit in Cardiothoracic Surgery Patients

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this