21-Jan-2022 - Public Library of Science (PLoS)

Machine learning model uses blood tests to predict COVID-19 survival

Levels of 14 proteins in the blood of critically ill COVID-19 patients are associated with survival

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 published in the open-access journal PLOS Digital Health by Florian Kurth and Markus Ralser of the Charité – Universitätsmedizin Berlin, Germany, and colleagues.

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 5 out of 5 patients who died (AUROC = 1.0, P = 0.000047).

The researchers conclude 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.

Facts, background information, dossiers
More about Public Library of Science
More about Charité
  • News

    Fungal infections: Microbial cooperation leads to drug tolerance

    The treatment of fungal infections is often hampered by fungal pathogens that do not respond, or are tolerant, against anti-fungal drugs. A team of researchers from Charité – Universitätsmedizin Berlin and the Francis Crick Institute have now identified microbial cooperation as one of the c ... more

    Cholesterol-lowering drugs may slow down metastases

    Researchers led by Ulrike Stein of the ECRC and Robert Preißner of Charité report in "Clinical and Translational Medicine" that these drugs inhibit a gene that promotes cancer cell metastasis. Cancer patients rarely die from the primary tumor but rather from the metastases – even after succ ... more

    Corona: New Insights into Antibody Response against Viral Variants

    In the journal Science, researchers from Charité – Universitätsmedizin Berlin and Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE) present new findings on the immune response against the coronavirus SARS-CoV-2. Their study is based on investigations of antibodies elicited by infe ... more

  • Research Institutes

    Charité - Universitätsmedizin Berlin

    The Charité is one of the largest university hospitals in Europe. Here, 3800 doctors and scientists heal, do research and teach at the top international level. More than half of the German Nobel Prize winners in medicine and physiology come from the Charité, among them Emil von Behring, Ro ... more