A data-driven computational methodology towards a pre-hospital Acute Ischaemic Stroke screening tool using haemodynamics waveforms

BACKGROUND AND OBJECTIVE

Acute Ischaemic Stroke (AIS), a significant global health concern, results from occlusions in cerebral arteries, causing irreversible brain damage. Different type of treatments exist depending on the size and location of the occlusion. Challenges persist in achieving faster diagnosis and treatment, which needs to happen in the first hours after the onset of symptoms to maximize the chances of patient recovery. The current diagnostic pipeline, i.e. "drip and ship", involves diagnostic via advanced imaging tools, only available in large clinical facilities, which poses important delays. This study investigates the feasibility of developing a machine learning model to diagnose and locate occluding blood clots from velocity waveforms, which can be easily be obtained with portable devices such as Doppler Ultrasound. The goal is to explore this approach as a cost-effective and time-efficient alternative to advanced imaging techniques typically available only in large hospitals.

METHODS

Simulated haemodynamic data is used to conduct blood flow simulations representing healthy and different AIS scenarios using a population-based database. A Machine Learning classification model is trained to solve the inverse problem, this is, detect and locate a potentially occluding thrombus from measured waveforms. The classification process involves two steps. First, the region where the thrombus is located is classified into nine groups, including healthy, left or right large vessel occlusion, left or right anterior cerebral artery, and left or right posterior cerebral artery. In a second step, the bifurcation generation of the thrombus location is classified as small, medium, or large vessel occlusion.

RESULTS

The proposed methodology is evaluated for data without noise, achieving a true prediction rate exceeding 95% for both classification steps mentioned above. The inclusion of up to 20% noise reduces the true prediction rate to 80% for region detection and 70% for bifurcation generation detection.

CONCLUSIONS

This study demonstrates the potential effectiveness and efficiency of using haemodynamic data and machine learning to detect and locate occluding thrombi in AIS patients. Although the geometric and topological data used in this study are idealized, the results suggest that this approach could be applicable in real-world situations with appropriate adjustments. Source code is available in https://github.com/ahmetsenemse/Acute-Ischaemic-Stroke-screening-tool-.

Perfluorocarbon Enhanced Glasgow Oxygen Level Dependent (GOLD) Magnetic Resonance Metabolic Imaging Identifies the Penumbra Following Acute Ischemic Stroke

The ability to identify metabolically active and potentially salvageable ischaemic penumbra is crucial for improving treatment decisions in acute stroke patients. Our solution involves two complementary novel MRI techniques (Glasgow Oxygen Level Dependant (GOLD) Metabolic Imaging), which when combined with a perfluorocarbon (PFC) based oxygen carrier and hyperoxia can identify penumbra due to dynamic changes related to continued metabolism within this tissue compartment. Our aims were (i) to investigate whether PFC offers similar enhancement of the second technique (Lactate Change) as previously demonstrated for the T₂*OC technique (ii) to demonstrate both GOLD metabolic imaging techniques working concurrently to identify penumbra, following administration of Oxycyte^® (O-PFC) with hyperoxia.

Methods: An established rat stroke model was utilised. Part-1: Following either saline or PFC, magnetic resonance spectroscopy was applied to investigate the effect of hyperoxia on lactate change in presumed penumbra. Part-2; rats received O-PFC prior to T₂*OC (technique 1) and MR spectroscopic imaging, which was used to identify regions of tissue lactate change (technique 2) in response to hyperoxia. In order to validate the techniques, imaging was followed by [¹⁴C]2-deoxyglucose autoradiography to correlate tissue metabolic status to areas identified as penumbra.

Results: Part-1: PFC+hyperoxia resulted in an enhanced reduction of lactate in the penumbra when compared to saline+hyperoxia. Part-2: Regions of brain tissue identified as potential penumbra by both GOLD metabolic imaging techniques utilising O-PFC, demonstrated maintained glucose metabolism as compared to adjacent core tissue.

Conclusion: For the first time in vivo, enhancement of both GOLD metabolic imaging techniques has been demonstrated following intravenous O-PFC+hyperoxia to identify ischaemic penumbra. We have also presented preliminary evidence of the potential therapeutic benefit offered by O-PFC. These unique theranostic applications would enable treatment based on metabolic status of the brain tissue, independent of time from stroke onset, leading to increased uptake and safer use of currently available treatment options.