Clinical Report: Utilizing Machine Learning Algorithms to Identify Risk Factors for Rebleeding in the Acute Phase of Intracerebral Hemorrhage

Overview

This study investigates risk factors for rebleeding in patients with intracerebral hemorrhage using machine learning models.

Background

Intracerebral hemorrhage (ICH) is a significant subtype of stroke associated with high morbidity and mortality rates.

Data Highlights

Key Findings

• Statistically significant differences in rebleeding risk factors were identified between rebleeding and non-rebleeding groups.
• The GBDT model achieved an AUC of 0.967 in the validation set.
• The final 10-variable GBDT model had an AUC of 0.85 on the test set.
• Bootstrap internal validation yielded a mean AUC of 0.964.
• Top SHAP importance variables included HII, GCS, and age.

Clinical Implications

The developed GBDT model can assist clinicians in identifying high-risk patients for rebleeding after intracerebral hemorrhage. Early detection may facilitate timely interventions to improve patient outcomes.

Conclusion

The study presents a robust machine learning model for predicting rebleeding risk in acute intracerebral hemorrhage, emphasizing the importance of early identification of at-risk patients.

Related Resources & Content

1. Frontiers in Neurology, 2026 -- Development and internal validation of a machine learning model for predicting intracranial infection after spontaneous intracerebral hemorrhage: a two-center retrospective study
2. Frontiers in Neurology, 2026 -- Machine learning model for unfavorable outcome prediction in neurosurgical patients: the potential role of liver function markers
3. Frontiers in Endocrinology, 2026 -- Predicting mortality in non-traumatic intracerebral hemorrhage with glucose and lipid data
4. European Stroke Organisation (ESO) and European Association of Neurosurgical Societies (EANS) guideline on stroke due to spontaneous intracerebral haemorrhage
5. 2024 AHA/ASA Performance and Quality Measures for Spontaneous Intracerebral Hemorrhage: A Report From the American Heart Association/American Stroke Association
6. Frontiers in Neurology — Development of an automated machine learning-based prediction model and interactive tool for blood transfusion requirements in patients with severe traumatic brain injury
7. Andexanet for Factor Xa Inhibitor–Associated Acute Intracerebral Hemorrhage
8. Tranexamic acid versus placebo in individuals with intracerebral haemorrhage treated within 2 h of symptom onset (STOP-MSU)
9. European Stroke Organisation (ESO) and European Association of Neurosurgical Societies (EANS) guideline on stroke due to spontaneous intracerebral haemorrhage
10. 2024 AHA/ASA Performance and Quality Measures for Spontaneous Intracerebral Hemorrhage: A Report From the American Heart Association/American Stroke Association - PubMed
11. Frontiers | The clinical potential of radiomics to predict hematoma expansion in spontaneous intracerebral hemorrhage: a narrative review
12. Blend sign as a prognostic factor for spontaneous intracerebral hemorrhage: A systematic review and meta-analysis - PubMed
13. Machine learning for predicting hematoma expansion in spontaneous intracerebral hemorrhage: a systematic review and meta-analysis - PubMed