Study using AI reveals secondary bacterial pneumonia, not cytokine storm, found as key factor in COVID-19 fatalities – Neuroscience News

Summary: A recent study found that secondary bacterial pneumonia, rather than the much-discussed “cytokine storm,” is a significant factor in COVID-19-related deaths. Nearly half of the patients who required mechanical ventilation support were affected by this secondary bacterial infection.

By applying machine learning to analyze medical records, the researchers found that those who recovered from secondary pneumonia were more likely to survive, while unsolved cases increased their risk of mortality.

The study, which challenges the cytokine storm theory, highlights the importance of aggressively preventing and treating secondary bacterial pneumonia in critically ill patients.

Main aspects:

  1. Nearly half of COVID-19 patients who required mechanical ventilation support developed secondary bacterial pneumonia, which was a significant contributor to the deaths.
  2. Patients recovered from secondary bacterial pneumonia had a higher chance of survival, while those with unresolved cases were more likely to die.
  3. The study challenges the widely held belief that a ‘cytokine storm’ causes death in COVID-19 patients, underscoring the importance of prevention and aggressive treatment of secondary bacterial pneumonia in critically ill patients.

Source: Northwest University

Secondary bacterial infection of the lung (pneumonia) was extremely common in patients with COVID-19, affecting nearly half of patients requiring mechanical ventilation support.

By applying machine learning to medical record data, scientists at Northwestern University Feinberg School of Medicine found that secondary bacterial pneumonia that did not resolve was a key driver of death in patients with COVID-19. It can even exceed the death rates from the viral infection itself.

Scientists have also found evidence that COVID-19 does not cause a cytokine storm, so it is often thought to cause death.

The study was recently published inJournal of Clinical Investigation.

“Our study highlights the importance of preventing, seeking, and aggressively treating secondary bacterial pneumonia in critically ill patients with severe pneumonia, including those with COVID-19,” said senior author Dr. Benjamin Singer, professor associate of medicine at Northwestern University Feinberg School of Medicine and a pulmonary and critical care physician at Northwestern Medicine.

Researchers have found that nearly half of patients with COVID-19 develop ventilator-associated secondary bacterial pneumonia.

Those who recovered from their secondary pneumonia were more likely to live, while those whose pneumonia didn’t resolve were more likely to die, Singer said.

Our data suggest 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 it.

The study findings also negate the cytokine storm theory, said Singer, also a Lawrence Hicks professor of pulmonary medicine at Feinberg.

The term cytokine storm means overwhelming inflammation that causes organ failure in the lungs, kidneys, brain and other organs, Singer said.

If this were true, if the cytokine storm underlies the long hospital stays we see in patients with COVID-19, we would expect to see frequent transitions to states characterized by multiple organ failure. That’s not what we saw.

The study analyzed 585 patients in Northwestern Memorial Hospital’s intensive care unit (ICU) with severe pneumonia and respiratory failure, 190 of them with COVID-19.

Scientists have developed a new machine learning approach called CarpeDiem, which groups similar days of ICU patients into clinical states based on data from electronic health records.

This new approach, which is based on the concept of daily intensive care team shifts, allowed them to ask how complications such as bacterial pneumonia affected the course of the disease.

These patients or their surrogates agreed to enroll 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 group of critical care physicians used state-of-the-art analysis of lung samples collected in the clinical care setting to diagnose and judge the outcomes of secondary pneumonia events.

Applying machine learning and artificial intelligence to clinical data can be used to develop better ways to treat diseases like COVID-19 and to assist critical care physicians in managing these patients, said co-author of the study, Dr. Catherine Gao, an instructor in pulmonary disease and critical care medicine at Feinberg and a physician at Northwestern Medicine.

The importance of bacterial superinfection of the lung as a contributor to death in COVID-19 patients has been underestimated because most centers either did not look for it or only look at findings in terms of the presence or absence of bacterial superinfection, not whether the treatment is successful or not, said study co-author Dr. Richard Wunderink, who directs the Successful Clinical Response in Pneumonia Therapy Systems Biology Center at Northwestern.

The next step in the research will be to use molecular data from study samples and integrate it with machine learning approaches to understand why some patients continue to be cured of pneumonia and others do not.

The investigators also want to expand the technique to larger datasets and use the model to make predictions that can be reported at the bedside to improve care of critically ill patients.

Other Northwestern authors on the article include Nikolay S. Markov, Thomas Stoeger, Anna E. Pawlowski, Mengjia Kang, Prasanth Nannapaneni, Rogan A. Grant, Chiagozie Pickens, James M. Walter, Jacqueline M. Kruser, Luke V. Rasmussen, Daniel Schneider, Justin Starren, Helen K. Donnelly, Alvaro Donayre, Yuan Luo, Scott Budinger, and Alexander Misharin.

Financing: The study was supported by the Simpson Querrey Lung Institute for Translational Sciences and National Institutes of Health grant U19AI135964.

About this AI research news

Author: Marla Paolo
Source: Northwest University
Contact: Marla Paul – Northwestern University
Image: The image is credited to Neuroscience News

Original research: Free access.
“Machine learning links unresolved secondary pneumonia to mortality in patients with severe pneumonia, including COVID-19” by Benjamin Singer et al. Journal of Clinical Investigation


Machine learning links unresolved secondary pneumonia to mortality in patients with severe pneumonia, including COVID-19

BACKGROUND. Although guidelines promote the prevention and aggressive treatment of ventilator-associated pneumonia (VAP), the importance of VAP as a driver of outcomes in mechanically ventilated patients, including patients with severe COVID-19, remains unclear. We aimed to determine the contribution of unsuccessful VAP treatment to mortality in patients with severe pneumonia.

METHODS. We performed a single-center prospective cohort study of 585 mechanically ventilated patients with severe pneumonia and respiratory failure, 190 of whom had COVID-19, who underwent at least one bronchoalveolar lavage. A panel of critical care physicians judged pneumonia episodes and endpoints based on clinical and microbiological data. Given the relatively long length of ICU stay among patients with COVID-19, we have developed a machine learning approach called Carpe Diemwhich groups similar ICU patient-days into clinical states based on electronic health record data.

RESULTS.Carpe Diem revealed that the long length of ICU stay among patients with COVID-19 is attributable to long stays in clinical states characterized primarily by respiratory failure. While VAP was not associated with overall mortality, mortality was higher in patients with an episode of unsuccessfully treated VAP than with successfully treated VAP (76.4% versus 17.6%, P < 0.001). In all patients, including those with COVID-19, Carpe Diem demonstrated that unresolved VAP was associated with transitions to clinical states associated with higher mortality.

CONCLUSIONS. Unsuccessful treatment of VAP is associated with higher mortality. The relatively long length of stay among patients with COVID-19 is mainly due to prolonged respiratory insufficiency, putting them at a higher risk of VAP.


#Study #reveals #secondary #bacterial #pneumonia #cytokine #storm #key #factor #COVID19 #fatalities #Neuroscience #News

Leave a Comment