What question did this study set out to answer?

The aim is to identify and validate clinical trajectory classes of persistent acute hypoxemic respiratory failure (AHRF).

May 20, 2026Open Access

Reproducible clinical archetypes in acute respiratory failure: a multi-cohort trajectory analysis

DMDominic C. MarshallCleveland Clinic London AGAshleigh D. GreenImperial College London MKMatthieu KomorowskiCharing Cross Hospital

Key Points

The aim is to identify and validate clinical trajectory classes of persistent acute hypoxemic respiratory failure (AHRF).
Utilized a competing-risk latent class mixed model to analyze patient trajectories to day 14.
Employed a 12-variable XGBoost model for early prediction of trajectory classes.
Analyzed the prevalence of ARDS and hyperinflammatory subphenotypes among identified trajectory classes.
A four-class trajectory model was established, with mortality rates ranging from 0.3% to 100% across classes.
TC2 was most common in ARDS patients, while TC4 had the highest percentage of hyperinflammatory subphenotype (41-53%).
Early prediction achieved mean AUCs of ≥ 0.78 by day 3 in external cohorts.

Abstract

PURPOSE: Acute hypoxemic respiratory failure (AHRF) is common and biologically heterogeneous. Static phenotyping at a single time point does not capture illness evolution and risks stage-mixing; reproducible clinical course archetypes may address this. We aimed to identify, externally validate, and predict trajectory classes (TCs) of persistent AHRF. METHODS: to day 14 and time to ICU discharge/death were jointly modelled using a competing-risk latent class mixed model. Early TC prediction used a 12-variable XGBoost model. We explored prevalence of ARDS and hyperinflammatory subphenotypes between TCs. RESULTS: A four-class model provided optimal fit: (TC1) early recovery (0.3% 14-day mortality); (TC2) stable persistence (8% 14-day mortality); (TC3) biphasic improvement-deterioration (17% 14-day mortality); and (TC4) rapid decline (100% 14-day mortality). These archetypes generalized to external cohorts with high assignment certainty. TCs demonstrated distinct patterns in other clinical biomarker trajectories. TC4 was enriched for the hyperinflammatory subphenotype (41-53%), while TC2 was most common in patients with ARDS (50%). Early TC prediction models achieved mean AUCs ≥ 0.78 (0.70-0.86) by day 3 in external validation. CONCLUSIONS: Four reproducible oxygenation archetypes capture the 14-day course of persistent respiratory failure. By providing early prognostic value distinct from static baseline severity, these trajectories have the potential to guide therapeutic strategies, reduce patient heterogeneity in trials, and direct biological phenotyping.

Ask AI

Helpful

Bookmark

View Full Paper