A machine learning approach identifies unresolving secondary pneumonia as a contributor to mortality in patients with severe pneumonia, including COVID-19

Abstract

BackgroundPatients with severe SARS-CoV-2 pneumonia experience longer durations of critical illness yet similar mortality rates compared to patients with severe pneumonia secondary to other etiologies. As secondary bacterial infection is common in SARS-CoV-2 pneumonia, we hypothesized that unresolving ventilator-associated pneumonia (VAP) drives the apparent disconnect between length-of-stay and mortality rate among these patients.MethodsWe analyzed VAP in a prospective single-center observational study of 585 mechanically ventilated patients with suspected pneumonia, including 190 patients with severe SARS-CoV-2 pneumonia. We developed CarpeDiem, a novel machine learning approach based on the practice of daily ICU team rounds to identify clinical states for each of the 12,495 ICU patient-days in the cohort. We used the CarpeDiem approach to evaluate the effect of VAP and its resolution on clinical trajectories.FindingsPatients underwent a median [IQR] of 4 [2,7] transitions between 14 clinical states during their ICU stays. Clinical states were associated with differential hospital mortality. The long length-of-stay among patients with severe SARS-CoV-2 pneumonia was associated with prolonged stays in clinical states defined by severe respiratory failure and with a lower frequency of transitions between clinical states. In all patients, including those with COVID-19, unresolving VAP episodes were associated with transitions to unfavorable states and hospital mortality.InterpretationCarpeDiem offers a machine learning approach to examine the effect of VAP on clinical outcomes. Our findings suggest an underappreciated contribution of unresolving secondary bacterial pneumonia to outcomes in mechanically ventilated patients with pneumonia, including due to SARS-CoV-2.Abstract FigureGraphical abstractDisentangling the contributions of ICU complications and interventions to ICU outcomes. (A) Traditional approaches evaluate the ICU stay as a black box with severity of illness measured on presentation and dichotomized survival at an arbitrary time point (e.g., day 28) or on ICU or hospital discharge. Hence, the effect of intercurrent complications and interventions cannot be easily measured, a problem that is compounded when ICU stays are long or significantly differ between groups. (B) Defining the ICU course by clinical features during each day in the ICU permits the association of a complication or intervention with transitions toward clinical states associated with favorable or unfavorable outcomes.

A distinctive evolution of alveolar T cell responses is associated with clinical outcomes in unvaccinated patients with SARS-CoV-2 pneumonia

“…In contrast, T cell enrichment was associated with favorable clinical parameters, including respiratory system compliance, in patients with COVID-19. The resolution status of the pneumonia episode based on expert clinical adjudication (21) was linked to mortality in patients with severe SARS-CoV-2 pneumonia in our cohort (Supplemental Figure 3M-N), similar to our findings in the larger cohort of patients with severe pneumonia enrolled in the SCRIPT study (15). Expression of CD127 (the interleukin-7 receptor) and HLA-DR on peripheral blood T cells has been associated with outcomes in SARS-CoV-2 pneumonia, with CD127 correlating with less severe disease and better outcomes and HLA-DR correlating with worsened disease severity and poorer outcomes (9,22,23).…”

“…We hypothesized that TCR repertoire diversity would become more oligoclonal (i.e., narrow) in response to new pathogens encountered during secondary bacterial pneumonias. Indeed, whereas richness increased over the course of mechanical ventilation in the non-COVID-19 groups, we found a significant decrease in richness over time in the COVID-19 group (Supplemental Figure 12E), consistent with the greater risk of secondary bacterial pneumonia in patients with severe SARS-CoV-2 pneumonia relative to similarly ill patients with other causes of pneumonia and respiratory failure (14,15). Comparing patients with COVID-19 who survived to hospital discharge with those who did not, we observed a statistically significant difference in richness only in patients who were diagnosed with a secondary bacterial infection (superinfection or VAP) during their ICU course (Supplemental Figure 12F).…”

“…In contrast, we found an inverse association between BAL fluid neutrophilia and survival to hospital discharge (Supplemental Figure 3K). Patients with COVID-19 who died in the hospital had greater neutrophilia in late samples than those who survived hospitalization (Supplemental Figure 3L), possibly reflecting the higher risk of late ventilator-associated pneumonia (VAP) in COVID-19 compared with pneumonia due to other causes (14,15,20) (see Supplemental Figure 2P). Consistent with this hypothesis, neutrophilic enrichment positively correlated with inflammatory markers (procalcitonin, troponin, D-dimer), steroid administration, severity of illness (SOFA score), driving pressure, duration of mechanical ventilation, presence of superinfection, and hospital mortality in patients with COVID-19 (Figure 1G), but not in patients with other causes of pneumonia and respiratory failure (Supplemental Figure 4A-C).…”

“…Similar to prior reports (31)(32)(33), we found that TCR repertoire diversity trended lower as a function of age (Supplemental Figure 12D). Approximately 50% of patients with severe SARS-CoV-2 pneumonia develop a secondary bacterial pneumonia either as a superinfection or a de novo ventilator-associated pneumonia (VAP) following viral clearance (14,15). We hypothesized that TCR repertoire diversity would become more oligoclonal (i.e., narrow) in response to new pathogens encountered during secondary bacterial pneumonias.…”

An observational cohort study of bronchoalveolar lavage fluid galactomannan andAspergillusculture positivity in patients requiring mechanical ventilation

“…Study setting and participants: Patients were enrolled in the Successful Clinical Response in Pneumonia Therapy (SCRIPT) Systems Biology Center, a single-site, cohort study of mechanically ventilated patients hospitalized in the Northwestern Memorial Hospital (NMH) medical intensive care unit (MICU) who underwent BAL for suspected pneumonia. 15,16 This study was approved by the Northwestern University Institutional Review Board with study ID STU00204868. Current analysis includes patients hospitalized from June 2018 to March 2023.…”