XGBoost outperforms other machine learning models in diagnosing Sepsis-Associated Thrombocytopenia: a multicenter retrospective study
Among the evaluated algorithms, the XGBoost model demonstrated superior performance, achieving an AUROC of 98.60% in cross-validation and 97.50% in the test set, indicating the strongest performance metrics within internal validation.
Authors
- Devrim Bozkurt (ORCID: https://orcid.org/0000-0003-4557-3390)
- Kamil Gönderen
- Nur SOYER
- Caner Acar (ORCID: https://orcid.org/0000-0002-9782-6807)
- Evrim Özmen
- Sukriye Miray Kilincer Bozgul
- Busra Emir
- Mehmet Göktuğ Efgan
Institutions
- Izmir Kâtip Çelebi University (TR)
- Ege University (TR)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2026-02-09
- DOI
- https://doi.org/10.3389/fmed.2026.1715551
- Primary Topic
- Sepsis Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00