We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.

Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
Technopath Clinical Diagnostics - An LGC Company

Download Mobile App





Machine Learning Model Uses Blood Tests to Predict Survival of Critically Ill COVID-19 Patients

By LabMedica International staff writers
Posted on 20 Jan 2022
Print article
Image: Proteomics core facility at Charité University hospital Berlin (Photo courtesy of Johannes Hartl, Charité)
Image: Proteomics core facility at Charité University hospital Berlin (Photo courtesy of Johannes Hartl, Charité)

A single blood sample from a critically ill COVID-19 patient can be analyzed by a machine learning model which uses blood plasma proteins to predict survival, weeks before the outcome, according to a new study.

Scientists at the Charité-Universitätsmedizin Berlin (Berlin, Germany) have found that the levels of 14 proteins in the blood of critically ill COVID-19 patients are associated with survival. Healthcare systems around the world are struggling to accommodate high numbers of severely ill COVID-19 patients who need special medical attention, especially if they are identified as being at high risk. Clinically established risk assessments in intensive care medicine, such as the SOFA or APACHE II, show only limited reliability in predicting future disease outcomes for COVID-19.

In the new study, researchers studied the levels of 321 proteins in blood samples taken at 349 timepoints from 50 critically ill COVID-19 patients being treated in two independent health care centers in Germany and Austria. A machine learning approach was used to find associations between the measured proteins and patient survival. 15 of the patients in the cohort died; the average time from admission to death was 28 days. For patients who survived, the median time of hospitalization was 63 days.

The researchers pinpointed 14 proteins which, over time, changed in opposite directions for patients who survive compared to patients who do not survive on intensive care. The team then developed a machine learning model to predict survival based on a single time-point measurement of relevant proteins and tested the model on an independent validation cohort of 24 critically ill COVID-10 patients. The model demonstrated high predictive power on this cohort, correctly predicting the outcome for 18 of 19 patients who survived and five out of five patients who died.

The researchers concluded that blood protein tests, if validated in larger cohorts, may be useful in both identifying patients with the highest mortality risk, as well as for testing whether a given treatment changes the projected trajectory of an individual patient.

Related Links:
Charité-Universitätsmedizin Berlin 

Gold Supplier
SARS-CoV-2 Antigen Test
NG-Test SARS-NG-Test SARS-CoV-2 Ag Cassette
New
Electrolyte Analyzer
CARELYTE A-Series
New
SARS-CoV-2 IgG Antibodies Anti-S1 Assay
iRapid SARS-CoV-2 Quant "Neutralizing" Ab
New
Gold Supplier
Chemistry Analyzer
BS-600M

Print article

Channels

Clinical Chem.

view channel
Image: The analysis pipeline used to investigate associations between blood metabolites, later life brain imaging measures, and genetic risk for Alzheimer’s disease (Photo courtesy of University College London)

Lipid Measurements Show Potential as Alzheimer’s Disease Biomarkers

Brain changes accompanying ageing are varied and can include pathologies that lead to cognitive impairment, the commonest of which is Alzheimer’s disease (AD). Identifying blood-based signatures of brain... Read more

Molecular Diagnostics

view channel
Image: Researchers have identified 10 new genes linked with hearing loss (Photo courtesy of 123rf.com)

Newly Identified Genes May Help to Screen and Treat Individuals with Hearing Loss

A massive genome-wide association study (GWAS) identified 10 novel gene loci associated with hearing loss, which may aid in screening and treating the disorder. Hearing loss is one of the top contributors... Read more

Hematology

view channel
Image: The CS-2500 analyzer features pre-analytic sample checks and four detection methods simultaneously on a single platform – coagulation end-point, chromogenic kinetic analysis, turbidimetric immunoassay and automated platelet aggregation (Photo courtesy of Sysmex)

Microvascular/Endothelial Dysfunction Contributes to Post-COVID Syndrome Pathogenesis

Post-COVID syndrome (PCS) or Long-COVID is an increasingly recognized complication of acute SARS-CoV-2 infection, characterized by persistent fatigue, reduced exercise tolerance chest pain, shortness of... Read more

Industry

view channel
Image: Sales of lateral flow assays in clinical testing are expected to register a CAGR of 5% through 2032 (Photo courtesy of Pexels)

Global Lateral Flow Assays Market to Surpass USD 11.5 Billion by 2032 Due to Evolving Applications

The global lateral flow assays market was valued at USD 7.2 billion in 2021 and is projected to register a CAGR of 4.7% during 2022-2032 to surpass USD 11.7 billion by the end of 2032, driven by the growing... Read more
Copyright © 2000-2022 Globetech Media. All rights reserved.