Aneurysmal subarachnoid haemorrhage (aSAH) is a severe cerebrovascular condition frequently complicated by cerebral vasospasm (CV) and delayed cerebral ischemia (DCI), which significantly increase mortality, long-term disability, and healthcare costs. Despite advances in neurosurgical and neurocritical care, reliable early prediction of these secondary complications remains an unresolved clinical challenge. Current assessment methods rely on delayed physiological or imaging signs and do not fully exploit the predictive potential of routinely acquired multimodal imaging data.
The proposed research addresses this gap by developing and validating an explainable multimodal computational framework for early CV/DCI risk assessment based on routinely collected CT, CT angiography (CTA), and CT perfusion (CTP) data combined with clinical and laboratory variables. The project integrates advanced medical image analysis, vascular feature extraction, computational modelling concepts, and uncertainty-aware machine learning to enable anatomically resolved, interpretable risk estimation.
Project funding:
Research Council of Lithuania, Designated Programme “Information technologies for the development of science and knowledge society”
Project results:
The expected outcomes include harmonized multimodal datasets, validated analytical pipelines, and a semi-integrated research prototype suitable for simulated clinical workflow testing. The project will contribute to the development of explainable artificial intelligence (XAI) methods for complex biomedical data, strengthen interdisciplinary collaboration between engineering and clinical sciences, and enhance national research capacity in advanced medical data analytics.
In the long term, the results may support a transition from reactive to preventive neurocritical care strategies, reduce avoidable neurological injury, and foster the development of next-generation decision-support systems in precision medicine. The project will also contribute to training doctoral and graduate students, strengthening scientific competence in artificial intelligence, numerical modelling, and medical data science.
Period of project implementation: 2026-09-01 - 2028-08-31
Project coordinator: Kaunas University of Technology
Project partners: Lithuanian Energy Institute
