Explainable machine learning reveals multifactorial drivers of early intracranial hematoma progression in traumatic brain injury: development of a SHAP-guided SVM nomogram
We developed and validated an interpretable SVM model that accurately predicts early hematoma progression in TBI patients. By integrating demographic, radiological, and laboratory features, this model provides a reliable tool for early risk stratification, guiding individualized management and timely intervention. Its strong performance across subgroups underscores its clinical applicability.
Authors
- Xujie Wang (ORCID: https://orcid.org/0000-0001-8638-9878)
- Ziyi Zhao (ORCID: https://orcid.org/0009-0008-6548-7960)
- Rongfei Xie
- Xuhui Liu
- Minmin Li
- Zhaohui Liu
Institutions
- Sun Yat-sen University (CN)
- Chinese PLA General Hospital (CN)
- Qinghai University Affiliated Hospital (CN)
- Sun Yat-sen Memorial Hospital (CN)
- Lanzhou University Second Hospital (CN)
- First Affiliated Hospital of Chinese PLA General Hospital (CN)
- Anhui Academy of Coal Science (CN)
- China Coal Technology and Engineering Group Corp (China) (CN)
- Tianjin Medical University (CN)
- Lanzhou University (CN)
Publication Details
- Journal
- Frontiers in Neurology
- Published
- 2026-02-05
- DOI
- https://doi.org/10.3389/fneur.2026.1718794
- Primary Topic
- Intracerebral and Subarachnoid Hemorrhage Research
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Qinghai University