Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach

Bruno Ribeiro; Vitor Cerqueira; Ricardo Santos; Hugo Gamboa

doi:10.1109/EHB52898.2021.9657577

Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach

Bruno Ribeiro, Vitor Cerqueira, Ricardo Santos, Hugo Gamboa

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

2 Citations (Scopus)

Abstract

Precise machine learning models for the early identification of anomalies based on biosignal data retrieved from bedside monitors could improve intensive care, by helping clinicians make decisions in advance and produce on-time responses. However, traditional models show limitations when dealing with the high complexity of this task. Layered Learning (LL) emerges as a solution, as it consists of the hierarchical decomposition of the problem into simpler tasks. This paper explores the uncovered potential of LL in the early detection of Acute Hypotensive Episodes (AHEs). We leverage information from the MIMIC-III Database to test different subdivisions of the main task and study how to combine the outcomes from distinct layers. In addition to this, we also test a novel approach to reduce false positives in AHE predictions.

Original language	English
Title of host publication	2021 International Conference on e-Health and Bioengineering (EHB)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Number of pages	4
ISBN (Electronic)	978-1-6654-4000-4
ISBN (Print)	978-1-6654-4001-1
DOIs	https://doi.org/10.1109/EHB52898.2021.9657577
Publication status	Published - 2021
Event	9th IEEE International Conference on E-Health and Bioengineering Conference, EHB 2021 - Iasi, Romania Duration: 18 Nov 2021 → 19 Nov 2021

Publication series

Name	E-Health and Bioengineering Conference (EHB)
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)	2575-5137
ISSN (Electronic)	2575-5145

Conference

Conference	9th IEEE International Conference on E-Health and Bioengineering Conference, EHB 2021
Country/Territory	Romania
City	Iasi
Period	18/11/21 → 19/11/21

Keywords

Biosignal Processing
Intensive Care
Layered Learning
Machine Learning

Access to Document

10.1109/EHB52898.2021.9657577

Cite this

Ribeiro, B., Cerqueira, V., Santos, R., & Gamboa, H. (2021). Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach. In 2021 International Conference on e-Health and Bioengineering (EHB) (E-Health and Bioengineering Conference (EHB)). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/EHB52898.2021.9657577

@inproceedings{98782045bb87424a9ccdef445d13fa8f,

title = "Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach",

abstract = "Precise machine learning models for the early identification of anomalies based on biosignal data retrieved from bedside monitors could improve intensive care, by helping clinicians make decisions in advance and produce on-time responses. However, traditional models show limitations when dealing with the high complexity of this task. Layered Learning (LL) emerges as a solution, as it consists of the hierarchical decomposition of the problem into simpler tasks. This paper explores the uncovered potential of LL in the early detection of Acute Hypotensive Episodes (AHEs). We leverage information from the MIMIC-III Database to test different subdivisions of the main task and study how to combine the outcomes from distinct layers. In addition to this, we also test a novel approach to reduce false positives in AHE predictions. ",

keywords = "Biosignal Processing, Intensive Care, Layered Learning, Machine Learning",

author = "Bruno Ribeiro and Vitor Cerqueira and Ricardo Santos and Hugo Gamboa",

note = "Funding Information: info:eu-repo/grantAgreement/FCT/FCT_DSAIPA_2020/DSAIPA%2FAI%2F0094%2F2020/PT# ACKNOWLEDGMENT This work was supported by the project “CardioFollowAI: Value-Based Healthcare for Patients of Post-Cardiac Surgery”. Publisher Copyright: {\textcopyright} 2021 IEEE.; 9th IEEE International Conference on E-Health and Bioengineering Conference, EHB 2021 ; Conference date: 18-11-2021 Through 19-11-2021",

year = "2021",

doi = "10.1109/EHB52898.2021.9657577",

language = "English",

isbn = "978-1-6654-4001-1",

series = "E-Health and Bioengineering Conference (EHB)",

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

booktitle = "2021 International Conference on e-Health and Bioengineering (EHB)",

address = "United States",

}

Ribeiro, B, Cerqueira, V, Santos, R & Gamboa, H 2021, Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach. in 2021 International Conference on e-Health and Bioengineering (EHB). E-Health and Bioengineering Conference (EHB), Institute of Electrical and Electronics Engineers (IEEE), 9th IEEE International Conference on E-Health and Bioengineering Conference, EHB 2021, Iasi, Romania, 18/11/21. https://doi.org/10.1109/EHB52898.2021.9657577

Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach. / Ribeiro, Bruno; Cerqueira, Vitor; Santos, Ricardo et al.
2021 International Conference on e-Health and Bioengineering (EHB). Institute of Electrical and Electronics Engineers (IEEE), 2021. (E-Health and Bioengineering Conference (EHB)).

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

TY - GEN

T1 - Layered Learning for Acute Hypotensive Episode Prediction in the ICU

T2 - 9th IEEE International Conference on E-Health and Bioengineering Conference, EHB 2021

AU - Ribeiro, Bruno

AU - Cerqueira, Vitor

AU - Santos, Ricardo

AU - Gamboa, Hugo

N1 - Funding Information: info:eu-repo/grantAgreement/FCT/FCT_DSAIPA_2020/DSAIPA%2FAI%2F0094%2F2020/PT# ACKNOWLEDGMENT This work was supported by the project “CardioFollowAI: Value-Based Healthcare for Patients of Post-Cardiac Surgery”. Publisher Copyright: © 2021 IEEE.

PY - 2021

Y1 - 2021

N2 - Precise machine learning models for the early identification of anomalies based on biosignal data retrieved from bedside monitors could improve intensive care, by helping clinicians make decisions in advance and produce on-time responses. However, traditional models show limitations when dealing with the high complexity of this task. Layered Learning (LL) emerges as a solution, as it consists of the hierarchical decomposition of the problem into simpler tasks. This paper explores the uncovered potential of LL in the early detection of Acute Hypotensive Episodes (AHEs). We leverage information from the MIMIC-III Database to test different subdivisions of the main task and study how to combine the outcomes from distinct layers. In addition to this, we also test a novel approach to reduce false positives in AHE predictions.

AB - Precise machine learning models for the early identification of anomalies based on biosignal data retrieved from bedside monitors could improve intensive care, by helping clinicians make decisions in advance and produce on-time responses. However, traditional models show limitations when dealing with the high complexity of this task. Layered Learning (LL) emerges as a solution, as it consists of the hierarchical decomposition of the problem into simpler tasks. This paper explores the uncovered potential of LL in the early detection of Acute Hypotensive Episodes (AHEs). We leverage information from the MIMIC-III Database to test different subdivisions of the main task and study how to combine the outcomes from distinct layers. In addition to this, we also test a novel approach to reduce false positives in AHE predictions.

KW - Biosignal Processing

KW - Intensive Care

KW - Layered Learning

KW - Machine Learning

UR - http://www.scopus.com/inward/record.url?scp=85124506109&partnerID=8YFLogxK

U2 - 10.1109/EHB52898.2021.9657577

DO - 10.1109/EHB52898.2021.9657577

M3 - Conference contribution

AN - SCOPUS:85124506109

SN - 978-1-6654-4001-1

T3 - E-Health and Bioengineering Conference (EHB)

BT - 2021 International Conference on e-Health and Bioengineering (EHB)

PB - Institute of Electrical and Electronics Engineers (IEEE)

Y2 - 18 November 2021 through 19 November 2021

ER -

Layered Learning for Acute Hypotensive Episode Prediction in the ICU: An Alternative Approach

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this