Predicting thromboembolic complications in COVID-19 ICU patients using machine learning
Davy van de Sande1, Michel E van Genderen1, Babette Rosman1
1Department of Adult Intensive Care, Erasmus University Medical Center, Rotterdam, the Netherlands.
Journal of Clinical and Translational Research
|January 27, 2021
Summary
A decision tree model can predict thromboembolic complications (TCs) in COVID-19 patients admitted to the ICU. Early identification of TCs aids clinical decision-making and management of critically ill patients.
Area of Science:
- Critical Care Medicine
- Hematology
- Infectious Diseases
Background:
- The COVID-19 pandemic presents significant challenges for intensive care units (ICUs).
- Hypercoagulability is strongly associated with poor outcomes in COVID-19 patients.
- Effective management of COVID-19 requires early risk identification and accurate prognosis.
Purpose of the Study:
- To develop a predictive model for early identification of COVID-19 patients at risk of thromboembolic complications (TCs).
Main Methods:
- Analysis of electronic health records from 108 COVID-19 ICU patients.
- Development of a decision tree classifier using 66% of the data to predict TCs.
- Validation of the model on a test dataset.
Main Results:
- 40% of patients developed TCs, with higher mortality in the TC group (26% vs. 8%).
- Key predictors identified by the model include lactate dehydrogenase, standardized bicarbonate, albumin, and leukocytes.
- The model achieved 73% sensitivity and a positive likelihood ratio of 2.7 for predicting TCs 2 days prior.
Conclusions:
- Clinically relevant TCs are frequent in critically ill COVID-19 patients.
- A decision tree model can successfully predict TCs, aiding clinical decision-making.
- Further validation in larger populations is needed to determine generalizability and clinical impact.
Related Concept Videos
01:29Venous Thrombosis III: Interprofessional Care
115
Venous thrombosis requires effective prevention and treatment strategies to improve patient outcomes and reduce potential complications.Prevention StrategiesHealthcare providers must prioritize preventing venous thromboembolism (VTE) for all adult patients upon admission. Interventions depend on bleeding and thrombosis risk, medical history, current medications, diagnoses, planned procedures, and patient preferences. Patients on bed rest should change positions every two hours and, if not...
115
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
114
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...
114
01:29Pulmonary Embolism I: Introduction
262
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...
262
01:18Steps in Outbreak Investigation
346
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:
346