In its most severe form, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the virus that causes coronavirus disease 2019 (COVID-19), leads to a lif

Rationale: Two distinct phenotypes of acute respiratory distress syndrome (ARDS) with differential clinical outcomes and responses to randomly assigned treatment have consistently been identified in randomized controlled trial cohorts using latent class analysis. Plasma biomarkers, key components in phenotype identification, currently lack point-of-care assays and represent a barrier to the clinical implementation of phenotypes. Objectives: The objective of this study was to develop models to classify ARDS phenotypes using readily available clinical data only. Methods: Three randomized controlled trial cohorts served as the training data set (ARMA [High vs. Low Vt], ALVEOLI [Assessment of Low Vt and Elevated End-Expiratory Pressure to Obviate Lung Injury], and FACTT [Fluids and Catheter Treatment Trial]; n = 2,022), and a fourth served as the validation data set (SAILS [Statins for Acutely Injured Lungs from Sepsis]; n = 745). A gradient-boosted machine algorithm was used to develop classifier models using 24 variables (demographics, vital signs, laboratory, and respiratory variables) at enrollment. In two secondary analyses, the ALVEOLI and FACTT cohorts each, individually, served as the validation data set, and the remaining combined cohorts formed the training data set for each analysis. Model performance was evaluated against the latent class analysis–derived phenotype. Measurements and Main Results: For the primary analysis, the model accurately classified the phenotypes in the validation cohort (area under the receiver operating characteristic curve [AUC], 0.95; 95% confidence interval [CI], 0.94–0.96). Using a probability cutoff of 0.5 to assign class, inflammatory biomarkers (IL-6, IL-8, and sTNFR-1; P < 0.0001) and 90-day mortality (38% vs. 24%; P = 0.0002) were significantly higher in the hyperinflammatory phenotype as classified by the model. Model accuracy was similar when ALVEOLI (AUC, 0.94; 95% CI, 0.92–0.96) and FACTT (AUC, 0.94; 95% CI, 0.92–0.95) were used as the validation cohorts. Significant treatment interactions were observed with the clinical classifier model–assigned phenotypes in both ALVEOLI (P = 0.0113) and FACTT (P = 0.0072) cohorts. Conclusions: ARDS phenotypes can be accurately identified using machine learning models based on readily available clinical data and may enable rapid phenotype identification at the bedside.

Purpose of review: To provide an overview of the current research in identifying homogeneous subgroups and phenotypes in ARDS. Recent findings: In recent years, investigations have used either physiology, clinical data, biomarkers or a combination of these to stratify patients with ARDS into distinct subgroups with divergent clinical outcomes. In some studies, there has also been evidence of differential treatment response within subgroups. Physiologic approaches include stratification based on P/F ratio and ventilatory parameters; stratification based on P/F ratio is already being employed in clinical trials. Clinical approaches include stratification based on ARDS risk factor or direct vs. indirect ARDS. Combined clinical and biological data has been used to identify two phenotypes across five cohorts of ARDS, termed hyperinflammatory and hypoinflammatory. These phenotypes have widely divergent clinical outcomes and differential response to mechanical ventilation, fluid therapy, and simvastatin in secondary analysis of completed trials. Next steps in the field include prospective validation of inflammatory phenotypes and integration of high-dimensional ‘omics’ data into our understanding of ARDS heterogeneity. Summary: Identification of distinct subgroups or phenotypes in ARDS may impact future conduct of clinical trials and can enhance our understanding of the disorder, with potential future clinical implications.