The following is a summary of “Development of a biomarker prediction model for post-trauma multiple organ failure/dysfunction syndrome based on the blood transcriptome,” published in the August 2024 issue of Critical Care by Duran et al.

A leading cause of mortality and morbidity among patients undergoing severe trauma is multiple organ failure/dysfunction syndrome (MOF/MODS). Clinical practices implicating physiological measurements and clinical scoring systems are employed to diagnose its onset.

Researchers conducted a retrospective study to develop a prediction model for MOF outcomes evaluating traumatic injury by machine learning analysis of genome-wide transcriptome data from blood samples drawn within 24 h of injury and compared the model’s performance with baseline injury severity scores and infection detection methods.

They analyzed buffy coat transcriptome and clinical datasets from blunt trauma patients with Inflammation and the Host Response to Injury Study (“Glue Grant”). Based on the inclusion/exclusion criteria, they examined 141 adult patients with blunt trauma (age ≥ 16 years) with early buffy coat samples (≤ 24 hours post-trauma), including 58 MOF cases and 83 non-cases. The Least absolute shrinkage and selection operator (LASSO) and eXtreme Gradient Boosting (XGBoost) algorithms were applied to develop early MOF outcome prediction models.

The results showed 18 transcripts of The LASSO model (AUROC [95% CI]: 0.938 [0.890–0.987] (training) and 0.833 [0.699–0.967] (test)), and 41 transcripts of XGBoost model (0.999 [0.997–1.000] (training) and 0.907 [0.816–0.998] (test)). There were 16 overlapping transcripts comparing the two panels (0.935 [0.884–0.985] (training) and 0.836 [0.703–0.968] (test)). The biomarkers which outperformed based on injury severity scores and sex were significantly associated with MOF (APACHE II + sex—0.649 [0.537–0.762] (training) and 0.493 [0.301–0.685] (test); ISS + sex—0.630 [0.516–0.744] (training) and 0.482 [0.293–0.670] (test); NISS + sex—0.651 [0.540–0.763] (training) and 0.525 [0.335–0.714] (test)).

They concluded the assessment of MOF from blood samples withdrawn immediately after trauma was expected to improve clinical decision-making and could contribute to reduced morbidity, mortality, and healthcare costs.

Source: annalsofintensivecare.springeropen.com/articles/10.1186/s13613-024-01364-5