Northwestern University researchers have identified secondary bacterial pneumonia as a major driver of COVID-19 deaths in critically ill patients. The findings of their machine learning (ML)-based analysis of medical record data suggest that secondary bacterial pneumonia, which affects around half of critically ill COVID-19 patients, is often underappreciated. The researchers found that successful treatment of secondary pneumonia was significantly correlated with patient outcomes and that mortality related to the virus itself is relatively low. The study highlights the importance of looking for and treating secondary bacterial pneumonia in COVID-19 patients.
The COVID-19 pandemic has affected millions of people worldwide and caused hundreds of thousands of deaths. While much research has focused on understanding the virus and developing treatments, a study by researchers at Northwestern University has shed light on a previously underappreciated contributor to COVID-19 mortality: secondary bacterial pneumonia. This article will provide a detailed analysis of the study, which was published in the Journal of Clinical Investigation.
Background
A respiratory disease called COVID-19 is brought on by the SARS-CoV-2 virus. The virus primarily targets the respiratory system, but it can also cause damage to other organs, such as the heart and kidneys. In severe cases, COVID-19 can lead to acute respiratory distress syndrome (ARDS), which can be fatal. While the virus itself has been the primary focus of research, the study by Northwestern University researchers highlights the importance of secondary bacterial pneumonia as a driver of COVID-19 mortality.
Study Design
The study, which was published in the Journal of Clinical Investigation, analyzed medical record data from 585 patients with severe pneumonia and respiratory failure in the intensive care unit (ICU) at Northwestern Memorial Hospital who were enrolled in the Successful Clinical Response to Pneumonia Therapy (SCRIPT) study. Of these patients, 190 had COVID-19. The study also used lung samples taken from individuals as part of SCRIPT to aid in the diagnosis and evaluation of secondary pneumonia occurrences.
Using an ML tool known as CarpeDiem, the research team grouped similar ICU patient days into clinical states using information from each patient’s electronic health record (EHR). This approach, based on the concept of ICU daily rounds, enabled the researchers to evaluate how complications like pneumonia ‘superinfection’ impacted the trajectory of a patient’s COVID-19 infection.
Findings
The study found that secondary bacterial pneumonia was a major driver of COVID-19 deaths in critically ill patients. The subsequent bacterial pneumonia that struck about half of the COVID-19 patients who were seriously ill was linked to a greater mortality rate. The success or failure of treatment for secondary pneumonia was also significantly correlated with outcomes for patients in the study cohort. 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 researchers also found no evidence of a cytokine storm, a phenomenon that has been proposed as a major driver of COVID-19 mortality. If cytokine storm were underlying the long length of stay seen in patients with COVID-19, the researchers would have expected to see frequent transitions to states that are characterized by multi-organ failure. However, that was not what they observed in the data.
