Longitudinal respiratory subphenotypes in patients with COVID-19-related acute respiratory distress syndrome: results from three observational cohorts

Abstract

Background: Patients with COVID-19-related acute respiratory distress syndrome (ARDS) have been postulated to present with distinct respiratory subphenotypes. However, most phenotyping schema have been limited by sample size, disregard for temporal dynamics, and insufficient validation. We aimed to identify respiratory subphenotypes of COVID-19-related ARDS using unbiased data-driven approaches.

Methods: PRoVENT-COVID was an investigator-initiated, national, multicentre, prospective, observational cohort study at 22 intensive care units (ICUs) in the Netherlands. Consecutive patients who had received invasive mechanical ventilation for COVID-19 (aged 18 years or older) served as the derivation cohort, and similar patients from two ICUs in the USA served as the replication cohorts. COVID-19 was confirmed by positive RT-PCR. We used latent class analysis to identify subphenotypes using clinically available respiratory data cross-sectionally at baseline, and longitudinally using 8-hourly data from the first 4 days of invasive ventilation. We used group-based trajectory modelling to evaluate trajectories of individual variables and to facilitate potential clinical translation. The PRoVENT-COVID study is registered with ClinicalTrials.gov, NCT04346342.

Findings: Between March 1, 2020, and May 15, 2020, 1007 patients were admitted to participating ICUs in the Netherlands, and included in the derivation cohort. Data for 288 patients were included in replication cohort 1 and 326 in replication cohort 2. Cross-sectional latent class analysis did not identify any underlying subphenotypes. Longitudinal latent class analysis identified two distinct subphenotypes. Subphenotype 2 was characterised by higher mechanical power, minute ventilation, and ventilatory ratio over the first 4 days of invasive mechanical ventilation than subphenotype 1, but PaO2/FiO2, pH, and compliance of the respiratory system did not differ between the two subphenotypes. 185 (28%) of 671 patients with subphenotype 1 and 109 (32%) of 336 patients with subphenotype 2 had died at day 28 (p=0·10). However, patients with subphenotype 2 had fewer ventilator-free days at day 28 (median 0, IQR 0-15 vs 5, 0-17; p=0·016) and more frequent venous thrombotic events (109 [32%] of 336 patients vs 176 [26%] of 671 patients; p=0·048) compared with subphenotype 1. Group-based trajectory modelling revealed trajectories of ventilatory ratio and mechanical power with similar dynamics to those observed in latent class analysis-derived trajectory subphenotypes. The two trajectories were: a stable value for ventilatory ratio or mechanical power over the first 4 days of invasive mechanical ventilation (trajectory A) or an upward trajectory (trajectory B). However, upward trajectories were better independent prognosticators for 28-day mortality (OR 1·64, 95% CI 1·17-2·29 for ventilatory ratio; 1·82, 1·24-2·66 for mechanical power). The association between upward ventilatory ratio trajectories (trajectory B) and 28-day mortality was confirmed in the replication cohorts (OR 4·65, 95% CI 1·87-11·6 for ventilatory ratio in replication cohort 1; 1·89, 1·05-3·37 for ventilatory ratio in replication cohort 2).

Interpretation: At baseline, COVID-19-related ARDS has no consistent respiratory subphenotype. Patients diverged from a fairly homogenous to a more heterogeneous population, with trajectories of ventilatory ratio and mechanical power being the most discriminatory. Modelling these parameters alone provided prognostic value for duration of mechanical ventilation and mortality.

Funding: Amsterdam UMC.

Conflict of interest statement

Declaration of interests LDJB reports grants from the Dutch Lung Foundation (Young Investigator grant), grants from the Dutch Lung Foundation and Health Holland (Public–Private Partnership grant), grants from the Dutch Lung Foundation (Dirkje Postma Award), grants from the IMI COVID19 iniative, and grants from Amsterdam UMC fellowship, outside the submitted work. All other authors declare no competing interests.

Copyright © 2021 Elsevier Ltd. All rights reserved.

Figures

Figure 1

Study statistical methods to identify subphenotypes Summary of statistical analysis methods to model heterogeneity in respiratory variables. (A) The x-axis shows different timepoints. The y-axis shows different patients. The z-axis shows different variables. (B) Cross-sectional latent class analysis was done on each timepoint using multiple variables and did not yield any subphenotypes. (C) Longitudinal LCA was done on all timepoints combined using multiple variables and yielded two subphenotypes with differences in dynamics of mechanical power and ventilatory ratio. Subphenotype 2 had less ventilator-free days and more venous thrombotic events, but no difference in mortality. (D) GBTM was used to evaluate individual trajectories over all timepoints of a single variable. An upward trajectory of ventilatory ratio matched with the longitudinal LCA dynamics and was also associated with more venous thrombotic events, higher mortality, and fewer ventilator-free days. GBTM=group-based trajectory modelling. LCA=latent class analysis. MP=mechanical power. VR=ventilatory ratio. VTE=venous thrombotic events.

Figure 2

Standardised mean differences between the two longitudinal respiratory subphenotypes

Figure 3

Comparison of dynamic changes of time dependent latent class analysis subphenotypes and trajectory analysis At each 8-hourly timepoint the median and IQR is plotted. The line shows second-degree polynomial regression.