Neuroanesthesia & neurocritical care
Development and validation of intracranial hypertension prediction models based on radiomic features in patients with traumatic brain injury: an exploratory study based on CENTER-TBI data
Authors' conclusion
We successfully established a model for predicting intracranial hypertension on the basis of radiomic features.
Study context
- Population
- Traumatic brain injury (TBI) patients admitted to intensive care unit (ICU) with intracranial pressure (ICP) monitoring; development cohort from CENTER-TBI, validation cohort from Shanghai General Hospital
- Comparison
- Morphological, first-order, second-order, third-order and comprehensive radiomic models (logistic regression (LR) classifier)
- Outcome
- Intracranial hypertension (initial recorded ICP ≥20 mmHg) predicted from head computed tomography (CT)
Methodological detailsexploratory, radiomics
- Exploratory
- Radiomics
Performance
As reported in the abstract
Prediction of intracranial hypertension, external validation (LR classifier)
| Test or model | AUC | F1 score |
|---|---|---|
| Morphological model | 0.75 | 0.54 |
| First-order model | 0.77 | 0.73 |
| Second-order model | 0.76 | 0.63 |
| Third-order model | 0.86 | 0.72 |
| Comprehensive model | 0.83 | 0.75 |
AUC
Morphological model0.75
First-order model0.77
Second-order model0.76
Third-order model0.86
Comprehensive model0.83
F1 score
Morphological model0.54
First-order model0.73
Second-order model0.63
Third-order model0.72
Comprehensive model0.75
Original publication
Development and validation of intracranial hypertension prediction models based on radiomic features in patients with traumatic brain injury: an exploratory study based on CENTER-TBI data. Crit Care. Published 6 March 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →