The cytokine storm It is an excessive reaction of the immune system against an infection in which too many cytokines – proteins that are responsible for organizing the immune response – are released into the blood, causing great inflammation and can be fatal. Many of the people with COVID-19 grave presented this complication that was considered to be the main cause of his death. However, a group of scientists has found that what really killed the COVID patients was the bacterial pneumonia secondary not resolved.
Secondary bacterial infection of the lung (pneumonia) very frequently affected patients with COVID-19 and, specifically, it was experienced by almost half of those who required life support. mechanic ventilation. Now, researchers at Northwestern University Feinberg School of Medicine have applied machine learning to medical record data and found that unresolved secondary bacterial pneumonia was a key risk factor for COVID-19 patients. died, which could even exceed mortality rates from the viral infection itself.
“Our study highlights the importance of aggressively preventing, searching for, and treating secondary bacterial pneumonia in critically ill patients with severe pneumonia, including those with COVID-19,” said Dr. Dr. Benjamin Singerassociate professor of medicine at Northwestern Feinberg University and a pulmonary and critical care physician at Northwestern Medicine and lead author of the study, the results of which have been published in Journal of Clinical Investigation.
“The importance of bacterial superinfection of the lung as a contributor to death in patients with COVID-19 has been underestimated”
These scientists have verified that around half of the patients with COVID-19 develop a Secondary ventilator-associated bacterial pneumonia. “Those who were cured of their secondary pneumonia were more likely to live, while those whose pneumonia did not resolve were more likely to die,” Singer says. “Our data suggested that mortality related to the virus itself is relatively low, but other things that happen during the ICU stay, such as secondary bacterial pneumonia, make up for that.”
Artificial intelligence to improve disease treatment
Singer says his findings also refute the cytokine storm theory as a cause of death in COVID patients. “The term ‘cytokine storm’ refers to overwhelming inflammation that leads to organ failure in the lungs, kidneys, brain, and other organs,” he explains. “If that were true, if the cytokine storm was the basis for the long stay that we see in COVID-19 patients, we would expect to see frequent transitions to states that are characterized by multi-organ failure. That’s not what we saw.”
The researchers analyzed 585 patients with severe pneumonia and respiratory failure admitted to the intensive care unit (ICU) at Northwestern Memorial Hospital, 190 of whom had COVID-19. They developed a new machine learning approach called CarpeDiem, which groups days of ICU patients with a similar clinical state. This novel approach, which relies on electronic health record data from the ICU team’s daily rounds, allowed them to learn how complications such as bacterial pneumonia affected the course of the disease.
With the consent of the patients, they were enrolled in the Successful Clinical Response to Pneumonia Therapy (SCRIPT) study, an observational study to identify new biomarkers and therapies for patients with severe pneumonia. As part of SCRIPT, an expert panel of ICU physicians used state-of-the-art analysis of lung samples taken as part of clinical care to diagnose and adjudicate the outcomes of secondary pneumonia events.
“The application of machine learning and artificial intelligence to clinical data can be used to develop better ways to treat diseases like COVID-19 and help ICU doctors manage these patients”, has pointed out the co-author of the study, the Dra. Catherine Gaoan instructor in pulmonary and critical care medicine at Feinberg and a Northwestern Medicine physician.
“The importance of bacterial superinfection of the lung as a contributor to death in patients with COVID-19 has been underestimated because most centers have not looked for it, or only analyze the results in terms of the presence or absence of bacterial superinfection, not whether the treatment is successful or not,” said study co-author Dr. Dr. Richard Wunderinkwho directs the Center for Systems Biology of Successful Clinical Response in Pneumonia Therapy at Northwestern.
The researchers’ new goal is to use molecular data from the study samples and integrate it with machine learning approaches to find out why some patients are cured of pneumonia and others are not. In addition, they want to apply the technique to larger data sets and use the model to make predictions that help improve care for critically ill patients.