A recent study conducted by researchers at Northwestern University Feinberg School of Medicine in the US suggests that secondary bacterial pneumonia, rather than a “cytokine storm,” is a key driver of death in patients with COVID-19. By using machine learning to analyze medical record data, the researchers found that almost half of the patients who required support from mechanical ventilation developed secondary bacterial pneumonia, which may even exceed death rates from the SARS-CoV-2 viral infection itself.
The study, published in the Journal of Clinical Investigation, analyzed 585 patients in the intensive care unit (ICU) at Northwestern Memorial Hospital with severe pneumonia and respiratory failure, 190 of whom had COVID-19. Using a new machine learning approach called CarpeDiem, the researchers were able to group similar ICU patient-days into clinical states based on electronic health record data, allowing them to ask how complications like bacterial pneumonia impacted the course of illness.
“Our study highlights the importance of preventing, looking for, and aggressively treating secondary bacterial pneumonia in critically ill patients with severe pneumonia, including those with COVID-19,” said study senior author Benjamin Singer, an associate professor at Northwestern University Feinberg School of Medicine. “Those who were cured of their secondary pneumonia were likely to live, while those whose pneumonia did not resolve were more likely to die.”
The study’s findings also negate the cytokine storm theory, which posits that a severe immune reaction in which the body releases too many cytokines into the blood too quickly is the main cause of mortality in COVID-19 patients. “If cytokine storm were underlying the long length of stay we see in patients with COVID-19, we would expect to see frequent transitions to states that are characterized by multi-organ failure. That’s not what we saw,” said Singer.
The researchers hope that their novel approach to analyzing clinical data using machine learning and artificial intelligence can be used to develop better ways to treat diseases like COVID-19 and to assist ICU physicians managing these patients.