Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies

Background/Objectives: This study develops machine learning (ML) models to predict hypoxemia severity during emergency triage, particularly in Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) scenarios, using physiological data from medical-grade sensors. Methods: Tree-based models...

Full description

Saved in:
Bibliographic Details
Main Authors: Santino Nanini, Mariem Abid, Yassir Mamouni, Arnaud Wiedemann, Philippe Jouvet, Stephane Bourassa
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Diagnostics
Subjects:
Online Access:https://www.mdpi.com/2075-4418/14/23/2763
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850106844854353920
author Santino Nanini
Mariem Abid
Yassir Mamouni
Arnaud Wiedemann
Philippe Jouvet
Stephane Bourassa
author_facet Santino Nanini
Mariem Abid
Yassir Mamouni
Arnaud Wiedemann
Philippe Jouvet
Stephane Bourassa
author_sort Santino Nanini
collection DOAJ
description Background/Objectives: This study develops machine learning (ML) models to predict hypoxemia severity during emergency triage, particularly in Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) scenarios, using physiological data from medical-grade sensors. Methods: Tree-based models (TBMs) such as XGBoost, LightGBM, CatBoost, Random Forests (RFs), Voting Classifier ensembles, and sequential models (LSTM, GRU) were trained on the MIMIC-III and IV datasets. A preprocessing pipeline addressed missing data, class imbalances, and synthetic data flagged with masks. Models were evaluated using a 5-min prediction window with minute-level interpolations for timely interventions. Results: TBMs outperformed sequential models in speed, interpretability, and reliability, making them better suited for real-time decision-making. Feature importance analysis identified six key physiological variables from the enhanced NEWS2+ score and emphasized the value of mask and score features for transparency. Voting Classifier ensembles showed slight metric gains but did not outperform individually optimized models, facing a precision-sensitivity tradeoff and slightly lower F1-scores for key severity levels. Conclusions: TBMs were effective for real-time hypoxemia prediction, while sequential models, though better at temporal handling, were computationally costly. This study highlights ML’s potential to improve triage systems and reduce alarm fatigue, with future plans to incorporate multi-hospital datasets for broader applicability.
format Article
id doaj-art-d707a8a2dd094e28a6b22457bbdd120d
institution OA Journals
issn 2075-4418
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Diagnostics
spelling doaj-art-d707a8a2dd094e28a6b22457bbdd120d2025-08-20T02:38:43ZengMDPI AGDiagnostics2075-44182024-12-011423276310.3390/diagnostics14232763Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE EmergenciesSantino Nanini0Mariem Abid1Yassir Mamouni2Arnaud Wiedemann3Philippe Jouvet4Stephane Bourassa5Clinical Decision Support System Articificial Intelligence Health Cluster in Acute Child Care, PE-DIATRICS, CHU Ste-Justine Centre Hospitalier Universitaire Mère-Enfant, 3175 Boulevard de la Côte-Sainte-Catherine Drive, Montréal, QC H3T 1C5, CanadaClinical Decision Support System Articificial Intelligence Health Cluster in Acute Child Care, PE-DIATRICS, CHU Ste-Justine Centre Hospitalier Universitaire Mère-Enfant, 3175 Boulevard de la Côte-Sainte-Catherine Drive, Montréal, QC H3T 1C5, CanadaFaculté des arts et des sciences, Département d’informatique et de recherche opérationnelle (DIRO), Université de Montréal, 3150 Rue Jean-Brillant, Montréal, QC H3T 1N8, CanadaResearch Center CHU Ste-Justine Centre Hospitalier Universitaire Mère-Enfant, 3175 Boulevard de la Côte-Sainte-Catherine Drive, Montréal, QC H3T 1C5, CanadaResearch Center CHU Ste-Justine Centre Hospitalier Universitaire Mère-Enfant, 3175 Boulevard de la Côte-Sainte-Catherine Drive, Montréal, QC H3T 1C5, CanadaResearch Center CHU Ste-Justine Centre Hospitalier Universitaire Mère-Enfant, 3175 Boulevard de la Côte-Sainte-Catherine Drive, Montréal, QC H3T 1C5, CanadaBackground/Objectives: This study develops machine learning (ML) models to predict hypoxemia severity during emergency triage, particularly in Chemical, Biological, Radiological, Nuclear, and Explosive (CBRNE) scenarios, using physiological data from medical-grade sensors. Methods: Tree-based models (TBMs) such as XGBoost, LightGBM, CatBoost, Random Forests (RFs), Voting Classifier ensembles, and sequential models (LSTM, GRU) were trained on the MIMIC-III and IV datasets. A preprocessing pipeline addressed missing data, class imbalances, and synthetic data flagged with masks. Models were evaluated using a 5-min prediction window with minute-level interpolations for timely interventions. Results: TBMs outperformed sequential models in speed, interpretability, and reliability, making them better suited for real-time decision-making. Feature importance analysis identified six key physiological variables from the enhanced NEWS2+ score and emphasized the value of mask and score features for transparency. Voting Classifier ensembles showed slight metric gains but did not outperform individually optimized models, facing a precision-sensitivity tradeoff and slightly lower F1-scores for key severity levels. Conclusions: TBMs were effective for real-time hypoxemia prediction, while sequential models, though better at temporal handling, were computationally costly. This study highlights ML’s potential to improve triage systems and reduce alarm fatigue, with future plans to incorporate multi-hospital datasets for broader applicability.https://www.mdpi.com/2075-4418/14/23/2763hypoxemiamachine learningpatient triagedisaster managementCBRNE eventsVIMY Multi-System
spellingShingle Santino Nanini
Mariem Abid
Yassir Mamouni
Arnaud Wiedemann
Philippe Jouvet
Stephane Bourassa
Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies
Diagnostics
hypoxemia
machine learning
patient triage
disaster management
CBRNE events
VIMY Multi-System
title Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies
title_full Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies
title_fullStr Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies
title_full_unstemmed Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies
title_short Machine and Deep Learning Models for Hypoxemia Severity Triage in CBRNE Emergencies
title_sort machine and deep learning models for hypoxemia severity triage in cbrne emergencies
topic hypoxemia
machine learning
patient triage
disaster management
CBRNE events
VIMY Multi-System
url https://www.mdpi.com/2075-4418/14/23/2763
work_keys_str_mv AT santinonanini machineanddeeplearningmodelsforhypoxemiaseveritytriageincbrneemergencies
AT mariemabid machineanddeeplearningmodelsforhypoxemiaseveritytriageincbrneemergencies
AT yassirmamouni machineanddeeplearningmodelsforhypoxemiaseveritytriageincbrneemergencies
AT arnaudwiedemann machineanddeeplearningmodelsforhypoxemiaseveritytriageincbrneemergencies
AT philippejouvet machineanddeeplearningmodelsforhypoxemiaseveritytriageincbrneemergencies
AT stephanebourassa machineanddeeplearningmodelsforhypoxemiaseveritytriageincbrneemergencies