Rationale: The acute respiratory distress syndrome (ARDS) is a heterogenous condition, and identification of subphenotypes may help in better risk stratification.
Objectives: Identify ARDS subphenotypes using new simpler methodology and readily available clinical variables.
Design: Retrospective Cohort Study of ARDS trials.
Setting: Data from the U.S. ARDSNet trials and from the international ART trial.
Participants: 3763 patients from ARDSNet datasets and 1010 patients from the ART dataset.
Primary and secondary outcome measures: The primary outcome was 60-day or 28-day mortality, depending on what was reported in the original trial. K-means cluster analysis was performed to identify subgroups. For feature selection, sets. Sets of candidate variables were tested to assess their ability to produce different probabilities for mortality in each cluster. Clusters were compared to biomarker data, allowing identification of subphenotypes.
Results: Data from 4,773 patients was analyzed. Two subphenotypes (A and B) resulted in optimal separation in the final model, which included nine routinely collected clinical variables, namely: heart rate, mean arterial pressure, respiratory rate, bilirubin, bicarbonate, creatinine, PaO2, arterial pH, and FiO2. Participants in subphenotype B showed increased levels of pro-inflammatory markers, had consistently higher mortality, lower number of ventilator-free days at day 28, and longer duration of ventilation compared to patients in the subphenotype A.
Conclusions: Routinely available clinical data can successfully identify two distinct subphenotypes in adult ARDS patients. This work may facilitate implementation of precision therapy in ARDS clinical trials.
A Standardized SOA for Clinical Data Sharing to Support Acute Care, Telemedicine and Clinical Trials