Predicting pulmonary embolism among hospitalized patients with machine learning algorithms
Logan Ryan1, Jenish Maharjan1, Samson Mataraso1
1Dascena, Inc. Houston Texas USA.
Pulmonary Circulation
|May 4, 2022
Summary
A new machine learning algorithm can predict pulmonary embolisms (PE) in hospitalized patients before clinical symptoms appear. This predictive tool, utilizing XGBoost, offers improved early detection for better patient outcomes.
Area of Science:
- Medical informatics
- Machine learning in healthcare
- Cardiovascular medicine
Background:
- Pulmonary embolism (PE) is a critical, life-threatening condition requiring prompt diagnosis.
- Current risk stratification methods for PE are insufficient for predicting events proactively.
- Early identification is crucial for improving patient outcomes in PE cases.
Purpose of the Study:
- To develop and evaluate a machine learning algorithm (MLA) for predicting PE in inpatients before clinical detection.
- To identify patients at high risk for PE using routinely collected electronic health record data.
Main Methods:
- Developed three machine learning models (logistic regression, neural network, XGBoost) using data from 63,798 inpatients.
- Input data included routine demographic, clinical, and laboratory information.
- Model performance was assessed using AUROC, sensitivity, and specificity.
Main Results:
- The XGBoost model achieved the highest predictive performance with an AUROC of 0.85, 81% sensitivity, and 70% specificity.
- Neural network and logistic regression models showed lower performance (AUROCs of 0.74 and 0.67, respectively).
Conclusions:
- The developed XGBoost-based MLA demonstrates strong potential for early PE prediction in hospitalized patients.
- This algorithm could enhance patient outcomes by enabling earlier diagnosis and treatment of PE.
Related Concept Videos
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
55
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...
55
01:29Pulmonary Embolism I: Introduction
70
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...
70
01:27Pulmonary Embolism III: Nursing Management
53
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...
53
01:18Steps in Outbreak Investigation
227
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
227