Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach
BackgroundStroke-associated Hospital Acquired Pneumonia (HAP) significantly impacts patient outcomes. This study explores the utility of machine learning models in predicting HAP in stroke patients, leveraging national registry data and SHapley Additive exPlanations (SHAP) analysis to identify key p...
Saved in:
| Main Author: | |
|---|---|
| Other Authors: | , , , |
| Format: | article |
| Published: |
2025
|
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1016/j.jstrokecerebrovasdis.2024.108200 https://www.sciencedirect.com/science/article/pii/S1052305724006438 http://hdl.handle.net/10576/64520 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1857415085969899520 |
|---|---|
| author | Abujaber, Ahmad A. |
| author2 | Yaseen, Said Nashwan, Abdulqadir J. Akhtar, Naveed Imam, Yahia |
| author2_role | author author author author |
| author_facet | Abujaber, Ahmad A. Yaseen, Said Nashwan, Abdulqadir J. Akhtar, Naveed Imam, Yahia |
| author_role | author |
| dc.creator.none.fl_str_mv | Abujaber, Ahmad A. Yaseen, Said Nashwan, Abdulqadir J. Akhtar, Naveed Imam, Yahia |
| dc.date.none.fl_str_mv | 2025-04-28T05:19:15Z 2025-02-28 |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | http://dx.doi.org/10.1016/j.jstrokecerebrovasdis.2024.108200 10523057 https://www.sciencedirect.com/science/article/pii/S1052305724006438 http://hdl.handle.net/10576/64520 2 34 1532-8511 |
| dc.language.none.fl_str_mv | en |
| dc.publisher.none.fl_str_mv | Elsevier |
| dc.rights.none.fl_str_mv | http://creativecommons.org/licenses/by/4.0/ info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Stroke Hospital-acquired pneumonia Machine learning Personalized stroke care Stroke outcomes |
| dc.title.none.fl_str_mv | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| dc.type.none.fl_str_mv | Article info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
| description | BackgroundStroke-associated Hospital Acquired Pneumonia (HAP) significantly impacts patient outcomes. This study explores the utility of machine learning models in predicting HAP in stroke patients, leveraging national registry data and SHapley Additive exPlanations (SHAP) analysis to identify key predictive factors. MethodsWe collected data from a national stroke registry covering January 2014 to July 2022, including 9,840 patients diagnosed with ischemic and hemorrhagic strokes. Five machine learning models were trained and evaluated: XGBoost, Random Forest, Support Vector Machine (SVM), Logistic Regression, and Artificial Neural Network (ANN). Performance was assessed using accuracy, precision, recall, F1-score, AUC, log loss, and Brier score. SHAP analysis was conducted to interpret model outputs. ResultsThe ANN model demonstrated superior performance, with an F1-score of 0.86 and an AUC of 0.94. SHAP analysis identified key predictors: stroke severity, admission location, Glasgow Coma score (GCS), systolic and diastolic blood pressure at admission, ethnicity, stroke type, mode of arrival, and age. Patients with higher stroke severity, dysphagia, and those arriving by ambulance were at increased risk for HAP. ConclusionThis study enhances our understanding of early predictive factors for HAP in stroke patients and underlines the potential of machine learning to improve clinical decision-making and personalized care. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | qu_d1c038a73e996628bf7752b0408619e0 |
| identifier_str_mv | 10523057 2 34 1532-8511 |
| language_invalid_str_mv | en |
| network_acronym_str | qu |
| network_name_str | Qatar University repository |
| oai_identifier_str | oai:qspace.qu.edu.qa:10576/64520 |
| publishDate | 2025 |
| publisher.none.fl_str_mv | Elsevier |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | http://creativecommons.org/licenses/by/4.0/ |
| spelling | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approachAbujaber, Ahmad A.Yaseen, SaidNashwan, Abdulqadir J.Akhtar, NaveedImam, YahiaStrokeHospital-acquired pneumoniaMachine learningPersonalized stroke careStroke outcomesBackgroundStroke-associated Hospital Acquired Pneumonia (HAP) significantly impacts patient outcomes. This study explores the utility of machine learning models in predicting HAP in stroke patients, leveraging national registry data and SHapley Additive exPlanations (SHAP) analysis to identify key predictive factors. MethodsWe collected data from a national stroke registry covering January 2014 to July 2022, including 9,840 patients diagnosed with ischemic and hemorrhagic strokes. Five machine learning models were trained and evaluated: XGBoost, Random Forest, Support Vector Machine (SVM), Logistic Regression, and Artificial Neural Network (ANN). Performance was assessed using accuracy, precision, recall, F1-score, AUC, log loss, and Brier score. SHAP analysis was conducted to interpret model outputs. ResultsThe ANN model demonstrated superior performance, with an F1-score of 0.86 and an AUC of 0.94. SHAP analysis identified key predictors: stroke severity, admission location, Glasgow Coma score (GCS), systolic and diastolic blood pressure at admission, ethnicity, stroke type, mode of arrival, and age. Patients with higher stroke severity, dysphagia, and those arriving by ambulance were at increased risk for HAP. ConclusionThis study enhances our understanding of early predictive factors for HAP in stroke patients and underlines the potential of machine learning to improve clinical decision-making and personalized care.The study was funded by the Medical Research Center at Hamad Medical Corporation (Grant: MRC-01-22-594) Acknowledgment : Open Access funding is provided by the Qatar National Library.Elsevier2025-04-28T05:19:15Z2025-02-28Articleinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfhttp://dx.doi.org/10.1016/j.jstrokecerebrovasdis.2024.10820010523057https://www.sciencedirect.com/science/article/pii/S1052305724006438http://hdl.handle.net/10576/645202341532-8511enhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:qspace.qu.edu.qa:10576/645202025-04-28T19:10:32Z |
| spellingShingle | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach Abujaber, Ahmad A. Stroke Hospital-acquired pneumonia Machine learning Personalized stroke care Stroke outcomes |
| status_str | publishedVersion |
| title | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| title_full | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| title_fullStr | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| title_full_unstemmed | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| title_short | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| title_sort | Prediction of stroke-associated hospital-acquired pneumonia: Machine learning approach |
| topic | Stroke Hospital-acquired pneumonia Machine learning Personalized stroke care Stroke outcomes |
| url | http://dx.doi.org/10.1016/j.jstrokecerebrovasdis.2024.108200 https://www.sciencedirect.com/science/article/pii/S1052305724006438 http://hdl.handle.net/10576/64520 |