Novel criteria to classify ARDS severity using a machine learning approach

Abstract

Background: Usually, arterial oxygenation in patients with the acute respiratory distress syndrome (ARDS) improves substantially by increasing the level of positive end-expiratory pressure (PEEP). Herein, we are proposing a novel variable [PaO₂/(FiO₂xPEEP) or P/FP_E] for PEEP ≥ 5 to address Berlin's definition gap for ARDS severity by using machine learning (ML) approaches.

Methods: We examined P/FP_E values delimiting the boundaries of mild, moderate, and severe ARDS. We applied ML to predict ARDS severity after onset over time by comparing current Berlin PaO₂/FiO₂ criteria with P/FP_E under three different scenarios. We extracted clinical data from the first 3 ICU days after ARDS onset (N = 2738, 1519, and 1341 patients, respectively) from MIMIC-III database according to Berlin criteria for severity. Then, we used the multicenter database eICU (2014-2015) and extracted data from the first 3 ICU days after ARDS onset (N = 5153, 2981, and 2326 patients, respectively). Disease progression in each database was tracked along those 3 ICU days to assess ARDS severity. Three robust ML classification techniques were implemented using Python 3.7 (LightGBM, RF, and XGBoost) for predicting ARDS severity over time.

Results: P/FP_E ratio outperformed PaO₂/FiO₂ ratio in all ML models for predicting ARDS severity after onset over time (MIMIC-III: AUC 0.711-0.788 and CORR 0.376-0.566; eICU: AUC 0.734-0.873 and CORR 0.511-0.745).

Conclusions: The novel P/FP_E ratio to assess ARDS severity after onset over time is markedly better than current PaO₂/FiO₂ criteria. The use of P/FP_E could help to manage ARDS patients with a more precise therapeutic regimen for each ARDS category of severity.

Keywords: Acute respiratory distress syndrome; Intensive care units; Lung severity; Machine learning; Prediction models.