Protective ventilation and outcomes of critically ill patients with COVID-19: a cohort study

Abstract

Background: Approximately 5% of COVID-19 patients develop respiratory failure and need ventilatory support, yet little is known about the impact of mechanical ventilation strategy in COVID-19. Our objective was to describe baseline characteristics, ventilatory parameters, and outcomes of critically ill patients in the largest referral center for COVID-19 in Sao Paulo, Brazil, during the first surge of the pandemic.

Methods: This cohort included COVID-19 patients admitted to the intensive care units (ICUs) of an academic hospital with 94 ICU beds, a number expanded to 300 during the pandemic as part of a state preparedness plan. Data included demographics, advanced life support therapies, and ventilator parameters. The main outcome was 28-day survival. We used a multivariate Cox model to test the association between protective ventilation and survival, adjusting for PF ratio, pH, compliance, and PEEP.

Results: We included 1503 patients from March 30 to June 30, 2020. The mean age was 60 ± 15 years, and 59% were male. During 28-day follow-up, 1180 (79%) patients needed invasive ventilation and 666 (44%) died. For the 984 patients who were receiving mechanical ventilation in the first 24 h of ICU stay, mean tidal volume was 6.5 ± 1.3 mL/kg of ideal body weight, plateau pressure was 24 ± 5 cmH₂O, respiratory system compliance was 31.9 (24.4-40.9) mL/cmH₂O, and 82% of patients were ventilated with protective ventilation. Noninvasive ventilation was used in 21% of patients, and prone, in 36%. Compliance was associated with survival and did not show a bimodal pattern that would support the presence of two phenotypes. In the multivariable model, protective ventilation (aHR 0.73 [95%CI 0.57-0.94]), adjusted for PF ratio, compliance, PEEP, and arterial pH, was independently associated with survival.

Conclusions: During the peak of the epidemic in Sao Paulo, critically ill patients with COVID-19 often required mechanical ventilation and mortality was high. Our findings revealed an association between mechanical ventilation strategy and mortality, highlighting the importance of protective ventilation for patients with COVID-19.

Keywords: COVID-19; Pneumonia, viral; SARS virus; Severe acute respiratory syndrome; Ventilation, artificial.

Fig. 1

Study participant flow. Flow of potentially eligible participants in the study, and final numbers included and analyzed

Fig. 2

Distribution of tidal volume vs. plateau pressure (A), driving pressure (B), and compliance (C) for each patient on the first 24 h of ICU admission. Protective levels of ventilation, defined as tidal volume of ≤8 mL/kg of ideal body weight and plateau pressure ≤ 30 cmH₂O, were applied to 82% of patients (lower left quadrant in panel A), and the combination of high plateau pressure (> 30 cmH₂O) and high tidal volume (> 8 mL/kg) was rare (upper right quadrant in A). Using a threshold of driving pressure of < 16 cmH₂O, 69% were ventilated within protective levels (lower left quadrant in B). We added subcentimetric random variability in B (driving pressure) to avoid overlapping of several points over the same value using the function geom_jitter, on the statistical program R

Fig. 2

Distribution of tidal volume vs. plateau pressure (A), driving pressure (B), and compliance (C) for each patient on the first 24 h of ICU admission. Protective levels of ventilation, defined as tidal volume of ≤8 mL/kg of ideal body weight and plateau pressure ≤ 30 cmH₂O, were applied to 82% of patients (lower left quadrant in panel A), and the combination of high plateau pressure (> 30 cmH₂O) and high tidal volume (> 8 mL/kg) was rare (upper right quadrant in A). Using a threshold of driving pressure of < 16 cmH₂O, 69% were ventilated within protective levels (lower left quadrant in B). We added subcentimetric random variability in B (driving pressure) to avoid overlapping of several points over the same value using the function geom_jitter, on the statistical program R

Fig. 3

ICU survival at 28 days according to the application of protective ventilation. Solid red line represents survival of patients who received protective ventilation on day 1, defined as tidal volume of less than or equal to 8 mL/kg of ideal body weight and plateau pressure less than or equal to 30 cmH₂O; solid blue line represents the survival of patients who were ventilated with non-protective ventilation; the shaded area represents the 95% confidence intervals. The p value was obtained with a Cox proportional hazards model, adjusted for PF ratio, respiratory system compliance, pH, and PEEP