Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach

<h3>Objectives</h3><p dir="ltr">We aimed to build a machine learning predictive model to predict the risk of prolonged mechanical ventilation (PMV) for patients with Traumatic Brain Injury (TBI).</p><h3>Methods</h3><p dir="ltr">This study...

Full description

Saved in:
Bibliographic Details
Main Author: Ahmad Abujaber (9100064) (author)
Other Authors: Adam Fadlalla (9100067) (author), Diala Gammoh (9100070) (author), Husham Abdelrahman (768893) (author), Monira Mollazehi (9100073) (author), Ayman El-Menyar (440103) (author)
Published: 2020
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513554026070016
author Ahmad Abujaber (9100064)
author2 Adam Fadlalla (9100067)
Diala Gammoh (9100070)
Husham Abdelrahman (768893)
Monira Mollazehi (9100073)
Ayman El-Menyar (440103)
author2_role author
author
author
author
author
author_facet Ahmad Abujaber (9100064)
Adam Fadlalla (9100067)
Diala Gammoh (9100070)
Husham Abdelrahman (768893)
Monira Mollazehi (9100073)
Ayman El-Menyar (440103)
author_role author
dc.creator.none.fl_str_mv Ahmad Abujaber (9100064)
Adam Fadlalla (9100067)
Diala Gammoh (9100070)
Husham Abdelrahman (768893)
Monira Mollazehi (9100073)
Ayman El-Menyar (440103)
dc.date.none.fl_str_mv 2020-07-08T03:00:00Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0235231
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Using_trauma_registry_data_to_predict_prolonged_mechanical_ventilation_in_patients_with_traumatic_brain_injury_Machine_learning_approach/27924999
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biomedical and clinical sciences
Neurosciences
Information and computing sciences
Machine learning
Traumatic brain injury
Machine learning
Tracheostomy
Forecasting
Ventilators
Support vector machines
Artificial intelligence
Artificial neural networks
dc.title.none.fl_str_mv Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3>Objectives</h3><p dir="ltr">We aimed to build a machine learning predictive model to predict the risk of prolonged mechanical ventilation (PMV) for patients with Traumatic Brain Injury (TBI).</p><h3>Methods</h3><p dir="ltr">This study included TBI patients who were hospitalized in a level 1 trauma center between January 2014 and February 2019. Data were analyzed for all adult patients who received mechanical ventilation following TBI with abbreviated injury severity (AIS) score for the head region of ≥ 3. This study designed three sets of machine learning models: set A defined PMV to be greater than 7 days, set B (PMV > 10 days) and set C (PMV >14 days) to determine the optimal model for deployment. Patients’ demographics, injury characteristics and CT findings were used as predictors. Logistic regression (LR), Artificial neural networks (ANN) Support vector machines (SVM), Random Forest (RF) and C.5 Decision Tree (C.5 DT) were used to predict the PMV.</p><h3>Results</h3><p dir="ltr">The number of eligible patients that were included in the study were 674, 643 and 622 patients in sets A, B and C respectively. In set A, LR achieved the optimal performance with accuracy 0.75 and Area under the curve (AUC) 0.83. SVM achieved the optimal performance among other models in sets B with accuracy/AUC of 0.79/0.84 respectively. ANNs achieved the optimal performance in set C with accuracy/AUC of 0.76/0.72 respectively. Machine learning models in set B demonstrated more stable performance with higher prediction success and discrimination power.</p><h3>Conclusion</h3><p dir="ltr">This study not only provides evidence that machine learning methods outperform the traditional multivariate analytical methods, but also provides a perspective to reach a consensual definition of PMV.</p><h2>Other Information</h2><p dir="ltr">Published in: PLOS ONE<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1371/journal.pone.0235231" target="_blank">https://dx.doi.org/10.1371/journal.pone.0235231</a></p>
eu_rights_str_mv openAccess
id Manara2_e8449335d465b5f3f933a8545be99ce9
identifier_str_mv 10.1371/journal.pone.0235231
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/27924999
publishDate 2020
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approachAhmad Abujaber (9100064)Adam Fadlalla (9100067)Diala Gammoh (9100070)Husham Abdelrahman (768893)Monira Mollazehi (9100073)Ayman El-Menyar (440103)Biomedical and clinical sciencesNeurosciencesInformation and computing sciencesMachine learningTraumatic brain injuryMachine learningTracheostomyForecastingVentilatorsSupport vector machinesArtificial intelligenceArtificial neural networks<h3>Objectives</h3><p dir="ltr">We aimed to build a machine learning predictive model to predict the risk of prolonged mechanical ventilation (PMV) for patients with Traumatic Brain Injury (TBI).</p><h3>Methods</h3><p dir="ltr">This study included TBI patients who were hospitalized in a level 1 trauma center between January 2014 and February 2019. Data were analyzed for all adult patients who received mechanical ventilation following TBI with abbreviated injury severity (AIS) score for the head region of ≥ 3. This study designed three sets of machine learning models: set A defined PMV to be greater than 7 days, set B (PMV > 10 days) and set C (PMV >14 days) to determine the optimal model for deployment. Patients’ demographics, injury characteristics and CT findings were used as predictors. Logistic regression (LR), Artificial neural networks (ANN) Support vector machines (SVM), Random Forest (RF) and C.5 Decision Tree (C.5 DT) were used to predict the PMV.</p><h3>Results</h3><p dir="ltr">The number of eligible patients that were included in the study were 674, 643 and 622 patients in sets A, B and C respectively. In set A, LR achieved the optimal performance with accuracy 0.75 and Area under the curve (AUC) 0.83. SVM achieved the optimal performance among other models in sets B with accuracy/AUC of 0.79/0.84 respectively. ANNs achieved the optimal performance in set C with accuracy/AUC of 0.76/0.72 respectively. Machine learning models in set B demonstrated more stable performance with higher prediction success and discrimination power.</p><h3>Conclusion</h3><p dir="ltr">This study not only provides evidence that machine learning methods outperform the traditional multivariate analytical methods, but also provides a perspective to reach a consensual definition of PMV.</p><h2>Other Information</h2><p dir="ltr">Published in: PLOS ONE<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1371/journal.pone.0235231" target="_blank">https://dx.doi.org/10.1371/journal.pone.0235231</a></p>2020-07-08T03:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1371/journal.pone.0235231https://figshare.com/articles/journal_contribution/Using_trauma_registry_data_to_predict_prolonged_mechanical_ventilation_in_patients_with_traumatic_brain_injury_Machine_learning_approach/27924999CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/279249992020-07-08T03:00:00Z
spellingShingle Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
Ahmad Abujaber (9100064)
Biomedical and clinical sciences
Neurosciences
Information and computing sciences
Machine learning
Traumatic brain injury
Machine learning
Tracheostomy
Forecasting
Ventilators
Support vector machines
Artificial intelligence
Artificial neural networks
status_str publishedVersion
title Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
title_full Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
title_fullStr Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
title_full_unstemmed Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
title_short Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
title_sort Using trauma registry data to predict prolonged mechanical ventilation in patients with traumatic brain injury: Machine learning approach
topic Biomedical and clinical sciences
Neurosciences
Information and computing sciences
Machine learning
Traumatic brain injury
Machine learning
Tracheostomy
Forecasting
Ventilators
Support vector machines
Artificial intelligence
Artificial neural networks