Neuroanesthesia & neurocritical care
Interpretable machine learning model for outcome prediction in patients with aneurysmatic subarachnoid hemorrhage
Authors' conclusion
The novel deep learning model demonstrated strong predictive performance in determining functional outcomes in patients with aSAH
Study context
- Population
- Patients with aneurysmatic SAH treated at five hospitals in Japan
- Participants
- 718 patients · 5 hospitals
- Outcome
- Functional outcome (modified Rankin Scale scores)
Methodological detailsmulticentre, deep learning, SHAP interpretability
- Multicentre
- Deep learning
- SHAP interpretability
Performance
As reported in the abstract
Prediction of functional outcome (modified Rankin Scale) by the deep learning model
AUC of the model
0.90
Further findings
Validation (SHAP and logistic regression)
- SHAP supported importance of key features; logistic regression confirmed model robustness
Original publication
Interpretable machine learning model for outcome prediction in patients with aneurysmatic subarachnoid hemorrhage. Crit Care. Published 20 January 2025. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →