Related Experiment Video
Updated: Jan 17, 2026
07:44
A Porcine Model of Acute Autologous Pulmonary Embolism
Published on: September 6, 2024
770
Advancing Mortality Prediction in Pulmonary Embolism Using Machine Learning Algorithms-Systematic Review and
Pooya Eini1,2, Peyman Eini1, Homa Serpoush2
1Infectious Disease Research Center Hamadan University of Medical Sciences Hamadan Iran.
Pulmonary Circulation
|September 23, 2025
Summary
Machine learning models show excellent ability in predicting pulmonary embolism (PE) patient mortality, outperforming traditional methods. Advanced ML models and non-USA studies demonstrated higher sensitivity in this comprehensive meta-analysis.
Area of Science:
- Medical Informatics
- Cardiology
- Machine Learning
Background:
- Pulmonary embolism (PE) poses a significant mortality risk.
- Accurate mortality prediction is crucial for clinical decision-making in PE patients.
- Existing risk stratification tools have limitations in predicting PE mortality.
Purpose of the Study:
- To systematically review and meta-analyze the performance of machine learning (ML) models in predicting mortality among PE patients.
- To compare the discriminative ability of various ML algorithms for PE mortality prediction.
- To identify factors influencing the performance of ML models in PE mortality prediction.
Main Methods:
- Systematic review and meta-analysis of 17 studies involving 844,071 PE cases.
- Inclusion of studies evaluating ML models for PE mortality prediction.
- Pooled analysis of performance metrics including sensitivity, specificity, and AUROC.
Main Results:
- ML models demonstrated excellent discriminative ability with a pooled AUROC of 0.91.
- Pooled sensitivity was 0.88 and specificity was 0.79.
- Advanced ML models and non-USA studies showed higher sensitivity, while heterogeneity was noted, particularly in specificity.
Conclusions:
- Machine learning models significantly outperform traditional risk stratification tools for predicting PE mortality.
- ML models offer robust potential for enhancing clinical decision-making in PE management.
- Heterogeneity and retrospective study designs necessitate cautious interpretation of findings.
Related Concept Videos
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
329
Diagnosing Pulmonary EmbolismDiagnosing pulmonary embolism (PE) involves clinical assessment and advanced imaging tests. The preferred diagnostic tool is the spiral (helical) CT scan or CT angiography (CTA), which uses intravenous contrast media to visualize the pulmonary vasculature and identify emboli.A ventilation-perfusion (V/Q) scan is an alternative for patients unable to receive contrast media. This scan includes both perfusion and ventilation scanning. Perfusion scanning involves...
329
01:29Pulmonary Embolism I: Introduction
521
Pulmonary embolism (PE) occurs when a thrombus, fat or air embolus, amniotic fluid, or tumor tissue blocks one or more pulmonary arteries. These blockages originate in the venous system or the right side of the heart.EtiologyPE primarily arises from deep vein thrombosis (DVT) and other hypercoagulable states, such as inherited thrombophilias. Additional etiological factors include venous stasis, commonly seen in obesity, and endothelial injury from surgery and trauma. Less common causes include...
521
01:27Pulmonary Embolism III: Nursing Management
364
A pulmonary embolism occurs when a thrombus, amniotic fluid, tumor tissue, fat, or air embolus blocks one or more pulmonary arteries. Effective nursing management and patient education are crucial for improving outcomes and preventing recurrence.Nursing management starts with obtaining a comprehensive patient history, particularly noting any history of deep vein thrombosis (DVT). Assess for clinical manifestations, including dyspnea, chest pain, crackles, heart murmurs, and signs of right-sided...
364