Machine-learning algorithms identifies sTREM1 has a key biomarker for outcome prediction in critically ill
Charles de Roquetaillade1,2,3, Pierre-Louis Blot4,5, Fabrice Uhel6,7
1Université Paris Cité, Inserm U942 MASCOT, Paris, F-75006, France. charles.de-roquetaillade@aphp.fr.
Introduction:
Prognostic assessment in critically ill patients traditionally relies on severity scores or single biomarkers, each with limited ability to capture the biological heterogeneity of critical illness.
Objective:
To compare the prognostic performance of multiple biomarkers, individually and in combination with clinical variables, using machine learning approaches for the prediction of mortality and kidney-related outcomes.
Materials And Methods:
We performed a post-hoc analysis of the FROG-ICU cohort, a prospective observational study of patients admitted to ICUs. The study included critically ill patients who required invasive mechanical ventilation or a vasoactive agent for more than 24 h. The primary outcome was day-90 mortality, secondary outcome was major adverse kidney event (MAKE) in ICU. A total of 15 plasma biomarkers were evaluated using multiparametric approach. ML models involved Random Forest (RF) and LASSO regression. Mean decrease in accuracy was used to determine variable importance in RF model. External validation was performed in the MARS cohort which involved ICU patients admitted for sepsis and septic shock.
Results:
Among 2,061 patients in the FROG-ICU day-90 mortality was 30.1%. Machine learning models achieved AUCs of 0.74, outperforming severity scores (AUC 0.64, p < 0.001). Variable importance analysis consistently identified sTREM-1 as the strongest predictor. When evaluated alone, sTREM-1 demonstrated high prognostic performance (AUC 0.72), comparable to ML models. These findings were confirmed in the MARS cohort. Similar results were observed for MAKE prediction.
Conclusion:
sTREM-1 is a robust biomarker associated with mortality and kidney-related outcomes in critically ill patients. Its predictive performance were comparable to multiparametric machine learning models and superior to severity scores.
