GEMINI aims to deliver validated multi-organ and multi-scale computational models for treatment decision support and improved fundamental understanding of acute strokes, both ischaemic and haemorrhagic. We will demonstrate the added benefit of these computational models in personalised disease management. Specifically, GEMINI will deliver validated, integrated multi-scale, multi-organ Digital Twin in Healthcare (DTH) models for cerebral blood and cerebrospinal fluid flow, brain perfusion and metabolism, and blood flow and thrombosis along the heart-brain axis by integrating available and newly developed dynamic, interoperable, and modular computational models. Building on these models, GEMINI will deliver validated population-based DTHs of ischemic and haemorrhagic stroke aetiology and onset, treatment, and disease progression. Utilising these population-based DTHs, GEMINI will validate five personalised subject-specific DTHs, (1) stroke treatment, and (2) disease progression DTHs for acute ischaemic stroke and (3) aneurysm treatment, (4) subarachnoid haemorrhage progression, and (5) unruptured intracranial aneurysm risk assessment DTHs for haemorrhagic stroke to guide patient care and long-term management. We will bring proof of value of digital twins by the evaluation of the ischaemic stroke treatment selection DTH in a multi-centre clinical trial, in which treatment and patient outcomes are compared in situations with and without the availability of a DTH. GEMINI will implement a project-wide structured approach for data harmonisation, curation, model validation, verification, and model certification of the DTHs. Several outcomes of GEMINI have a high value for clinical practice, medical device industry, and in enhancing research in the fields of (bio)medical and computer sciences, warranting an extensive valorisation strategy with adequate IP protection and versatile exploitation actions to enhance a wide adaptation of the results of GEMINI.

Stroke is the number one cause of disability in the Western world and the 3rd most common cause of death. Despite new treatment options with intra-arterial thrombectomy, still 2 out of 3 patients still have a poor outcome. The main goal of INSIST is to advance treatments of ischemic stroke and its introduction in clinical practice by realizing in silico clinical stroke trials in which stroke and treatment are modeled. We will generate virtual populations of stroke patients, generate and validate in silico models for intra-arterial thrombectomy, thrombosis and thrombolysis, and microvascular perfusion and neurological deterioration after stroke, and integrate the in silico models to realize an in silico clinical stroke trial. We are uniquely positioned by the availability of a large pool of clinical, imaging, histopathological, and outcome data from multiple recently finalized stroke trials, a large registry (totaling 4500 patients), and new trials that will start later this year (totaling 2500 patients). We will build a population model that takes this input to generate virtual populations of stroke patients addressing the wide variety of patient characteristics. We will build on existing and emerging in silico models to validate reusable models for stroke and stroke treatment with a strong interaction with experimenting modeling in laboratories. The in silico models and virtual populations will be combined to simulate clinical trials and validated by simulating and comparing finalized and currently running trials. The in silico models will be used to simulate clinical trials to evaluate effectiveness and safety of novel devices and medication, both for the device as well as the pharmacological industry. For the device industry, we will evaluate the optimal configuration of thrombectomy stents for reduction of thrombus fragmentation. From the perspective of the pharmacy industry, we will simulate the effect of increased TAFIa on the effectiveness of alteplase.