Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach
Community-acquired pneumonia (CAP) is associated with high mortality, and accurate diagnosis and risk prediction are essential for improving patient outcomes. Traditional diagnostic methods have limitations, prompting the use of machine learning (ML) to enhance diagnostic precision and treatment s...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Association of Basic Medical Sciences of Federation of Bosnia and Herzegovina
2025-07-01
|
| Series: | Biomolecules & Biomedicine |
| Subjects: | |
| Online Access: | https://www.bjbms.org/ojs/index.php/bjbms/article/view/12378 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849423336553054208 |
|---|---|
| author | Alaa Ali Ahmad R. Alsayed Nesrin Seder Yazun Jarrar Raed H. Altabanjeh Mamoon Zihlif Osama Abu Ata Anas Samara Malek Zihlif |
| author_facet | Alaa Ali Ahmad R. Alsayed Nesrin Seder Yazun Jarrar Raed H. Altabanjeh Mamoon Zihlif Osama Abu Ata Anas Samara Malek Zihlif |
| author_sort | Alaa Ali |
| collection | DOAJ |
| description |
Community-acquired pneumonia (CAP) is associated with high mortality, and accurate diagnosis and risk prediction are essential for improving patient outcomes. Traditional diagnostic methods have limitations, prompting the use of machine learning (ML) to enhance diagnostic precision and treatment strategies. This study aims to develop ML models to predict CAP etiology and mortality using clinical data to enable early intervention. A retrospective cohort study was conducted on 251 adult CAP patients admitted to two Jordanian hospitals between March 2021 and February 2024. Various clinical data were analyzed using ML techniques, including linear regression, random forest, SHapley Additive exPlanations (SHAP), lasso regression, mutual information analysis, logistic regression, and correlation analysis. Key predictors of CAP survival included zinc, vitamin C, enoxaparin, and insulin bolus. Mutual information analysis identified neutrophils, alanine transaminase, mean corpuscular volume, hemoglobin, and platelets as significant mortality predictors, while lasso regression highlighted meropenem, arterial blood gases, PCO₂, and platelet count. Logistic regression confirmed intensive care unit (ICU) stay, pH, pulmonary severity index, white blood cell (WBC) count, and bicarbonate levels as crucial variables. Interestingly, lymphocyte count emerged as the strongest predictor of bacterial CAP, conflicting with established knowledge that associates neutrophils with bacterial infections. However, findings related to HCO₃, blood urea nitrogen, and WBC levels were consistent with clinical expectations. SHAP analysis highlighted basophils and fever as key predictors. Further investigation is needed to resolve conflicting findings and optimize predictive models. ML offers promising applications for CAP prognosis but requires refinement to address discrepancies and improve reliability in clinical decision-making.
|
| format | Article |
| id | doaj-art-80998c573d214735bbbdc73b653169e7 |
| institution | Kabale University |
| issn | 2831-0896 2831-090X |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Association of Basic Medical Sciences of Federation of Bosnia and Herzegovina |
| record_format | Article |
| series | Biomolecules & Biomedicine |
| spelling | doaj-art-80998c573d214735bbbdc73b653169e72025-08-20T03:30:37ZengAssociation of Basic Medical Sciences of Federation of Bosnia and HerzegovinaBiomolecules & Biomedicine2831-08962831-090X2025-07-0110.17305/bb.2025.12378Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approachAlaa Ali0Ahmad R. Alsayed1Nesrin Seder2Yazun Jarrar3Raed H. Altabanjeh4Mamoon Zihlif5Osama Abu Ata6Anas Samara7Malek Zihlif8Department of Clinical Pharmacy and Therapeutics, Applied Science Private University, Amman, JordanDepartment of Clinical Pharmacy and Therapeutics, Applied Science Private University, Amman, JordanDepartment of Pharmaceutical Chemistry and Pharmacognosy, Applied Science Private University, Amman, JordanDepartment of Basic Medical Sciences, Faculty of Medicine, Al-Balqa Applied University, Al-Salt, JordanDepartment of Clinical Pharmacy and Therapeutics, Applied Science Private University, Amman, JordanDepartment of Internal Medicine, Section of Pulmonary, Islamic Hospital, Amman, JordanDepartment of Internal Medicine, Section of Infectious Diseases, Islamic Hospital, Amman, JordanDepartment of Software Engineering, Bethlehem University, Bethlehem, PalestineDepartment of Pharmacology, School of Medicine, The University of Jordan, Amman, Jordan Community-acquired pneumonia (CAP) is associated with high mortality, and accurate diagnosis and risk prediction are essential for improving patient outcomes. Traditional diagnostic methods have limitations, prompting the use of machine learning (ML) to enhance diagnostic precision and treatment strategies. This study aims to develop ML models to predict CAP etiology and mortality using clinical data to enable early intervention. A retrospective cohort study was conducted on 251 adult CAP patients admitted to two Jordanian hospitals between March 2021 and February 2024. Various clinical data were analyzed using ML techniques, including linear regression, random forest, SHapley Additive exPlanations (SHAP), lasso regression, mutual information analysis, logistic regression, and correlation analysis. Key predictors of CAP survival included zinc, vitamin C, enoxaparin, and insulin bolus. Mutual information analysis identified neutrophils, alanine transaminase, mean corpuscular volume, hemoglobin, and platelets as significant mortality predictors, while lasso regression highlighted meropenem, arterial blood gases, PCO₂, and platelet count. Logistic regression confirmed intensive care unit (ICU) stay, pH, pulmonary severity index, white blood cell (WBC) count, and bicarbonate levels as crucial variables. Interestingly, lymphocyte count emerged as the strongest predictor of bacterial CAP, conflicting with established knowledge that associates neutrophils with bacterial infections. However, findings related to HCO₃, blood urea nitrogen, and WBC levels were consistent with clinical expectations. SHAP analysis highlighted basophils and fever as key predictors. Further investigation is needed to resolve conflicting findings and optimize predictive models. ML offers promising applications for CAP prognosis but requires refinement to address discrepancies and improve reliability in clinical decision-making. https://www.bjbms.org/ojs/index.php/bjbms/article/view/12378Community-acquired pneumoniaCAPmachine learningMLmortality predictionrisk assessment |
| spellingShingle | Alaa Ali Ahmad R. Alsayed Nesrin Seder Yazun Jarrar Raed H. Altabanjeh Mamoon Zihlif Osama Abu Ata Anas Samara Malek Zihlif Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach Biomolecules & Biomedicine Community-acquired pneumonia CAP machine learning ML mortality prediction risk assessment |
| title | Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach |
| title_full | Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach |
| title_fullStr | Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach |
| title_full_unstemmed | Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach |
| title_short | Unveiling etiology and mortality risks in community-acquired pneumonia: A machine learning approach |
| title_sort | unveiling etiology and mortality risks in community acquired pneumonia a machine learning approach |
| topic | Community-acquired pneumonia CAP machine learning ML mortality prediction risk assessment |
| url | https://www.bjbms.org/ojs/index.php/bjbms/article/view/12378 |
| work_keys_str_mv | AT alaaali unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT ahmadralsayed unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT nesrinseder unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT yazunjarrar unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT raedhaltabanjeh unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT mamoonzihlif unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT osamaabuata unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT anassamara unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach AT malekzihlif unveilingetiologyandmortalityrisksincommunityacquiredpneumoniaamachinelearningapproach |