Associations of serum sTREM-1 and sTREM-2 with mortality and neurological prognosis in patients resuscitated from cardiac arrest: a machine learning-based approach
Serum sTREM-1 performed better than sTREM-2 to predict mortality and neurological outcome after ROSC. Furthermore, the newly developed XGBoost and RF models incorporating sTREM-1 and/or sTREM-2 demonstrated superior predictive accuracy compared to conventional clinical scoring systems.
Authors
- L J Wang
- Zheyuan Fan (ORCID: https://orcid.org/0000-0002-9471-9619)
- Ping Gong (ORCID: https://orcid.org/0000-0001-9910-7948)
- Ping Chen (ORCID: https://orcid.org/0000-0003-0274-5674)
- Dian Yu (ORCID: https://orcid.org/0009-0007-1464-7744)
- Wei Zhang
- Bao Fu
Institutions
- Zunyi Medical University (CN)
- Dalian Medical University (CN)
- Southern University of Science and Technology (CN)
- Second Affiliated Hospital of Dalian Medical University (CN)
- First Affiliated Hospital of Dalian Medical University (CN)
- Affiliated Hospital of Zunyi Medical College (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2026-03-03
- DOI
- https://doi.org/10.3389/fmed.2026.1717571
- Primary Topic
- Inflammation biomarkers and pathways
- Type
- article
- Field-Weighted Citation Impact
- 0.00