Determining Clinically-Viable Biomarkers for Ischaemic Stroke Through a Mechanistic and Machine Learning Approach

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-.

High resolution simulation of basilar artery infarct and flow within the circle of Willis

On a global scale, cerebro- and cardiovascular diseases have long been one of the leading causes of death and disability and their prevalence appears to be increasing in recent times. Understanding potential biomarkers and risk factors will help to identify individuals potentially at risk of suffering an ischemic stroke. However, the widely variable construction of the cerebral vasculature makes it difficult to provide a specific assessment without the knowledge of a patient's physiology. In this paper we use the 3D blood flow simulator HemeLB to study flow within three common structural variations of the circle of Willis during and in the moments after a blockage of the basilar artery. This tool, based on the lattice Boltzmann method, allows the 3D flow entering the basilar artery to be finely controlled to replicate the cessation of blood feeding this particular vessel-we demonstrate this with several examples including a sudden halt to flow and a gradual loss of flow over three heartbeat cycles. In this work we start with an individualised 3D representation of a full circle of Willis and then construct two further domains by removing the left or right posterior communicating arteries from this geometry. Our results indicate how, and how quickly, the circle of Willis is able to redistribute flow following such a stroke. Due to the choice of infarct, the greatest reduction in flow was observed in the posterior cerebral arteries where flow was reduced by up to 70% in some cases. The high resolution domains used in this study permit the velocity magnitude and wall shear stress to be analysed at key points during and following the stroke. The model we present here indicates how personalised vessels are required to provide the best insight into stroke risk for a given individual.

A multiscale computational framework to evaluate flow alterations during mechanical thrombectomy for treatment of ischaemic stroke

The treatment of ischaemic stroke increasingly relies upon endovascular procedures known as mechanical thrombectomy (MT), which consists in capturing and removing the clot with a catheter-guided stent while at the same time applying external aspiration with the aim of reducing haemodynamic loads during retrieval. However, uniform consensus on procedural parameters such as the use of balloon guide catheters (BGC) to provide proximal flow control, or the position of the aspiration catheter is still lacking. Ultimately the decision is left to the clinician performing the operation, and it is difficult to predict how these treatment options might influence clinical outcome. In this study we present a multiscale computational framework to simulate MT procedures. The developed framework can provide quantitative assessment of clinically relevant quantities such as flow in the retrieval path and can be used to find the optimal procedural parameters that are most likely to result in a favorable clinical outcome. The results show the advantage of using BGC during MT and indicate small differences between positioning the aspiration catheter in proximal or distal locations. The framework has significant potential for future expansions and applications to other surgical treatments.

In silicostudy of the effects of cerebral circulation on source localization using a dynamical anatomical atlas of the human head

Objective.This study focuses on the effects of dynamical vascular modeling on source localization errors in electroencephalography (EEG). Our aim of thisin silicostudy is to (a) find out the effects of cerebral circulation on the accuracy of EEG source localization estimates, and (b) evaluate its relevance with respect to measurement noise and interpatient variation.Approach.We employ a four-dimensional (3D + T) statistical atlas of the electrical properties of the human head with a cerebral circulation model to generate virtual patients with different cerebral circulatory conditions for EEG source localization analysis. As source reconstruction techniques, we use the linearly constraint minimum variance (LCMV) beamformer, standardized low-resolution brain electromagnetic tomography (sLORETA), and the dipole scan (DS).Main results.Results indicate that arterial blood flow affects source localization at different depths and with varying significance. The average flow rate plays an important role in source localization performance, while the pulsatility effects are very small. In cases where a personalized model of the head is available, blood circulation mismodeling causes localization errors, especially in the deep structures of the brain where the main cerebral arteries are located. When interpatient variations are considered, the results show differences up to 15 mm for sLORETA and LCMV beamformer and 10 mm for DS in the brainstem and entorhinal cortices regions. In regions far from the main arteries vessels, the discrepancies are smaller than 3 mm. When measurement noise is added and interpatient differences are considered in a deep dipolar source, the results indicate that the effects of conductivity mismatch are detectable even for moderate measurement noise. The signal-to-noise ratio limit for sLORETA and LCMV beamformer is 15 dB, while the limit is under 30 dB for DS.Significance.Localization of the brain activity via EEG constitutes an ill-posed inverse problem, where any modeling uncertainty, e.g. a slight amount of noise in the data or material parameter discrepancies, can lead to a significant deviation of the estimated activity, especially in the deep structures of the brain. Proper modeling of the conductivity distribution is necessary in order to obtain an appropriate source localization. In this study, we show that the conductivity of the deep brain structures is particularly impacted by blood flow-induced changes in conductivity because large arteries and veins access the brain through that region.