Machine learning-based prediction of one-year mortality in ischemic stroke patients

<h3>Background</h3><p dir="ltr">Accurate prediction of mortality following an ischemic stroke is essential for tailoring personalized treatment strategies. This study evaluates the effectiveness of machine learning models in predicting one-year mortality after an ischemic...

Full description

Saved in:
Bibliographic Details
Main Author: Ahmad Abujaber (9100064) (author)
Other Authors: Said Yaseen (22282366) (author), Yahia Imam (9617067) (author), Abdulqadir Nashwan (17380348) (author), Naveed Akhtar (4919398) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513539566206976
author Ahmad Abujaber (9100064)
author2 Said Yaseen (22282366)
Yahia Imam (9617067)
Abdulqadir Nashwan (17380348)
Naveed Akhtar (4919398)
author2_role author
author
author
author
author_facet Ahmad Abujaber (9100064)
Said Yaseen (22282366)
Yahia Imam (9617067)
Abdulqadir Nashwan (17380348)
Naveed Akhtar (4919398)
author_role author
dc.creator.none.fl_str_mv Ahmad Abujaber (9100064)
Said Yaseen (22282366)
Yahia Imam (9617067)
Abdulqadir Nashwan (17380348)
Naveed Akhtar (4919398)
dc.date.none.fl_str_mv 2024-11-14T09:00:00Z
dc.identifier.none.fl_str_mv 10.1093/oons/kvae011
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Machine_learning-based_prediction_of_one-year_mortality_in_ischemic_stroke_patients/30173008
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
Health sciences
Epidemiology
Health services and systems
ischemic stroke
mortality
machine learning
early prediction
personalized medicine
dc.title.none.fl_str_mv Machine learning-based prediction of one-year mortality in ischemic stroke patients
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <h3>Background</h3><p dir="ltr">Accurate prediction of mortality following an ischemic stroke is essential for tailoring personalized treatment strategies. This study evaluates the effectiveness of machine learning models in predicting one-year mortality after an ischemic stroke. </p><h3>Methods</h3><p dir="ltr">Five machine learning models were trained using data from a national stroke registry, with logistic regression demonstrating the highest performance. The SHapley Additive exPlanations (SHAP) analysis explained the model’s outcomes and defined the influential predictive factors. </p><h3>Results</h3><p dir="ltr">Analyzing 8183 ischemic stroke patients, logistic regression achieved 83% accuracy, 0.89 AUC, and an F1 score of 0.83. Significant predictors included stroke severity, pre-stroke functional status, age, hospital-acquired pneumonia, ischemic stroke subtype, tobacco use, and co-existing diabetes mellitus (DM). </p><h3>Discussion</h3><p dir="ltr">The model highlights the importance of predicting mortality in enhancing personalized stroke care. Apart from pneumonia, all predictors can serve the early prediction of mortality risk which supports the initiation of early preventive measures and in setting realistic expectations of disease outcomes for all stakeholders. The identified tobacco paradox warrants further investigation. </p><h3>Conclusion</h3><p dir="ltr">This study offers a promising tool for early prediction of stroke mortality and for advancing personalized stroke care. It emphasizes the need for prospective studies to validate these findings in diverse clinical settings.</p><h2>Other Information</h2><p dir="ltr">Published in: Oxford Open Neuroscience<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1093/oons/kvae011" target="_blank">https://dx.doi.org/10.1093/oons/kvae011</a></p>
eu_rights_str_mv openAccess
id Manara2_da778d5a96a9148346977ea3f2dbedfd
identifier_str_mv 10.1093/oons/kvae011
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30173008
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Machine learning-based prediction of one-year mortality in ischemic stroke patientsAhmad Abujaber (9100064)Said Yaseen (22282366)Yahia Imam (9617067)Abdulqadir Nashwan (17380348)Naveed Akhtar (4919398)Biomedical and clinical sciencesNeurosciencesHealth sciencesEpidemiologyHealth services and systemsischemic strokemortalitymachine learningearly predictionpersonalized medicine<h3>Background</h3><p dir="ltr">Accurate prediction of mortality following an ischemic stroke is essential for tailoring personalized treatment strategies. This study evaluates the effectiveness of machine learning models in predicting one-year mortality after an ischemic stroke. </p><h3>Methods</h3><p dir="ltr">Five machine learning models were trained using data from a national stroke registry, with logistic regression demonstrating the highest performance. The SHapley Additive exPlanations (SHAP) analysis explained the model’s outcomes and defined the influential predictive factors. </p><h3>Results</h3><p dir="ltr">Analyzing 8183 ischemic stroke patients, logistic regression achieved 83% accuracy, 0.89 AUC, and an F1 score of 0.83. Significant predictors included stroke severity, pre-stroke functional status, age, hospital-acquired pneumonia, ischemic stroke subtype, tobacco use, and co-existing diabetes mellitus (DM). </p><h3>Discussion</h3><p dir="ltr">The model highlights the importance of predicting mortality in enhancing personalized stroke care. Apart from pneumonia, all predictors can serve the early prediction of mortality risk which supports the initiation of early preventive measures and in setting realistic expectations of disease outcomes for all stakeholders. The identified tobacco paradox warrants further investigation. </p><h3>Conclusion</h3><p dir="ltr">This study offers a promising tool for early prediction of stroke mortality and for advancing personalized stroke care. It emphasizes the need for prospective studies to validate these findings in diverse clinical settings.</p><h2>Other Information</h2><p dir="ltr">Published in: Oxford Open Neuroscience<br>License: <a href="https://creativecommons.org/licenses/by/4.0/" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1093/oons/kvae011" target="_blank">https://dx.doi.org/10.1093/oons/kvae011</a></p>2024-11-14T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1093/oons/kvae011https://figshare.com/articles/journal_contribution/Machine_learning-based_prediction_of_one-year_mortality_in_ischemic_stroke_patients/30173008CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/301730082024-11-14T09:00:00Z
spellingShingle Machine learning-based prediction of one-year mortality in ischemic stroke patients
Ahmad Abujaber (9100064)
Biomedical and clinical sciences
Neurosciences
Health sciences
Epidemiology
Health services and systems
ischemic stroke
mortality
machine learning
early prediction
personalized medicine
status_str publishedVersion
title Machine learning-based prediction of one-year mortality in ischemic stroke patients
title_full Machine learning-based prediction of one-year mortality in ischemic stroke patients
title_fullStr Machine learning-based prediction of one-year mortality in ischemic stroke patients
title_full_unstemmed Machine learning-based prediction of one-year mortality in ischemic stroke patients
title_short Machine learning-based prediction of one-year mortality in ischemic stroke patients
title_sort Machine learning-based prediction of one-year mortality in ischemic stroke patients
topic Biomedical and clinical sciences
Neurosciences
Health sciences
Epidemiology
Health services and systems
ischemic stroke
mortality
machine learning
early prediction
personalized medicine