Machine-learning algorithms identify sTREM1 as a key biomarker for outcome prediction in critically ill
Charles de Roquetaillade, Pierre-Louis Blot, Fabrice Uhel, Louis Boutin, Jérôme Cartailler, Tom Van Der Poll, Etienne Gayat, Alexandre Mebazaa, Benjamin Chousterman · 2026
Read Machine-learning algorithms identify sTREM1 as a key biomarker for outcome prediction in critically ill by Charles de Roquetaillade, Pierre-Louis Blot, Fabrice Uhel, Louis Boutin, Jérôme Cartailler, Tom Van Der Poll, Etienne Gayat, Alexandre Mebazaa, Benjamin Chousterman (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13274116.txt.
Description
Charles de Roquetaillade and co-authors used machine learning to rank biomarkers in critically ill patients in a 2026 analysis. Prognosis in intensive care leans on severity scores or single markers, each blind to how varied critical illness is. The team tested fifteen blood markers, alone and with clinical data.
They reanalyzed a large prospective cohort of 2,061 patients who needed breathing machines or blood pressure drugs for over a day. Learning models beat standard severity scores at predicting death by day ninety. One marker, sTREM-1, stood out in every importance ranking, and alone it nearly matched the full models. Findings repeated in an outside sepsis cohort, and the marker also predicted major kidney events. The authors name it a robust single measure for intensive care prognosis.
Catalog record
| CREATOR | Charles de Roquetaillade, Pierre-Louis Blot, Fabrice Uhel, Louis Boutin, Jérôme Cartailler, Tom Van Der Poll, Etienne Gayat, Alexandre Mebazaa, Benjamin Chousterman |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 24 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |