Related Experiment Video
Updated: Jul 3, 2026
Visualization and Analysis of Blood Flow and Oxygen Consumption in Hepatic Microcirculation: Application to an Acute Hepatitis Model
Published on: August 4, 2012
Surveying haemoperfusion impact on COVID-19 from machine learning using Shapley values
Behzad Einollahi1, Mohammad Javanbakht2, Mehrdad Ebrahimi2
1Nephrology and Urology Research Center, Clinical Science Institute, Baqiyatallah University of Medical Sciences, Tehran, Iran. behzad.einollahi@gmail.com.
Haemoperfusion (HP) significantly improved outcomes for severe COVID-19 patients by reducing ventilation needs and mortality. This extracorporeal therapy effectively filters blood, showing a positive impact on patient survival and prognosis.
Area of Science:
- Extracorporeal therapies
- Critical care medicine
- Immunomodulation
Background:
- Severe COVID-19 is characterized by a cytokine storm, leading to organ damage.
- Haemoperfusion (HP) is an extracorporeal therapy designed to remove inflammatory mediators from the blood.
- Assessing the clinical efficacy of HP in severe COVID-19 is crucial for improving patient outcomes.
Purpose of the Study:
- To evaluate the clinical benefits of haemoperfusion (HP) in patients with severe COVID-19.
- To compare the outcomes of patients treated with standard care versus standard care plus HP.
- To utilize machine learning, specifically Shapley values, to understand the contribution of HP to patient prognosis.
Main Methods:
- A retrospective cohort study of 578 inpatients with severe COVID-19.
- Control group received standard corticosteroid treatment (Regimen I).
- HP group received standard corticosteroid treatment plus haemoperfusion using Cytosorb H300 (Regimen II), with session frequency based on chest CT findings. Machine learning models incorporated patient characteristics, medications, and clinical conditions to calculate Shapley values.
Main Results:
- Haemoperfusion (HP) group showed a favorable clinical response compared to the control group.
- One to three HP sessions reduced ventilation requirements and mortality rates in severe COVID-19 patients.
- HP was associated with significant reductions in inflammation markers (ferritin), creatinine, D-dimer, and WBC levels compared to the control group. Significant differences were observed in the use of various medications between groups (P < 0.05).
Conclusions:
- Haemoperfusion is a significant factor in predicting patient survival in severe COVID-19.
- HP demonstrated a positive impact on reducing inflammation and improving renal function markers.
- The study highlights the crucial role of HP as a therapeutic option for severe COVID-19 cases, influencing patient prognosis.
More Related Videos
Related Concept Videos
02:45Blood Transfusion and Agglutination
History
The history of blood transfusion dates back to the 17th century, when early attempts were made in animals. In 1818 James Blundell, a British doctor, performed the first successful human blood transfusion. Later in 1900, Karl...
01:20Blood Studies for Cardiovascular System I: Cardiac Biomarkers
The essential diagnostic tools for detecting myocardial necrosis and monitoring individuals suspected of having acute coronary syndrome (ACS) include:
Troponins
Troponins, particularly cardiac troponins I and T, are the most precise and sensitive markers of myocardial injury. They are detectable within 4-6 hours of myocardial injury and remain...