Rapid diagnosis and treatment of stroke is critical in improving outcomes for stroke, which is the leading cause of serious long-term disability globally. Stroke is the fourth largest cause of death in the UK and costs £25.6 billion annually. The most common type of stroke is a large vessel occlusion which is a clot lodged in a major artery in the brain. Multiple clinical studies to have shown that patients have the best outcomes when treated with mechanical thrombectomy. Thrombectomy is a medical procedure where a specialist physician removes a blood clot from a blocked artery by making a small incision in the groin or arm, and using a catheter (thin, flexible tube) to guide a device through blood vessels in the body to the clot in the brain for removal. However, there are still many risks involved in mechanical thrombectomy for the patient and the clinicians. For the patient, there are risks of injury to the blood vessels. To address these problems, we want to create a robotic system that can improve the accuracy, availability, and safety of thrombectomy. The system will provide the following benefits: \***More accurate clot removal:** Robots can be programmed to move with more precision than human hands, which can help to ensure that the clot is removed completely and can help to reduce the risk of damage that is caused during the procedure. \***Widen access to underserved populations:** Thrombectomies will not require the physical presence of a highly trained operator meaning that it will be easier and more cost-effective to enable access in remote areas at any time. \***Less exposure to radiation:** Clinicians are exposed to higher than normal levels of radiation to carry out these procedures that need to be carried out regularly to save lives. Through this project, Brainomix, the leading stroke AI company in the UK & Europe, and Nanoflex, a robotics spin-off from ETH Zurich, will partner to develop a novel platform to be able to delicately guide more effective devices through to clots.

"We have formed a consortium of collaborating hospitals and commercial companies with public and patient involvement and input from charities to enable us to work with the public and the NHS to best develop and test the use of Artificial Intelligence programmes to improve health care. We are working with university academics and NHS hospitals across the country, from the south-west into London and including the North of England and Scotland. Our programme includes predominantly UK based companies ranging in size from a few employees to hundreds. We aim to learn about the difficult areas of ethics and public acceptance for machine learning and decision making in health care, and the use of patient data by commercial companies. We will put in strict safeguards to ensure patients and all involved in health care are confident that their data is managed securely and in a manner that would meet with their approval. Our ambition is to develop a relationship with patients and the NHS that will enable improved development and use of Artificial Intelligence to enhance the delivery of safer, better care, with clinical and economic gains to the NHS. Our programme of work will include the analysis and testing of algorithms on data for which we already have patient consent, and the collection of new patient data for which we will gain consent. This data will be securely stored and made available under strict rules to our collaborating academics and universities, and to commercial companies. Once we have developed and tested the Artificial Intelligence algorithms we will then test them in the NHS following applications to, and approvals from Research Ethics Committees."

Worldwide annually, 13,000,000 patients suffer a stroke. Mechanical clot removal (endovascular treatment) is expected to increase from 1% to 10% of patients, as recent studies show it improves patient outcome. It costs up to £23,000 per patient, making patient selection crucial for its adoption. Brainomix has developed the medical imaging software, e-ASPECTS to automate the clinically validated ASPECTS method on plain CT brain scans,measuring existing stroke damage. Brainomix will build on its know-how to design, develop and validate perfusion-ASPECTS, up to getting certifications for clinical use. This will automate ASPECTS on perfusion CTs (which measure blood flow in the brain) to measure tissue at risk and identify patients who can benefit from mechanical reopening of the artery. Brainomix founders’ international reputation in stroke will ensure the successful development and clinical adoption of perfusion-ASPECTS.

Stroke is the third cause of death and the first cause of adult disability in the UK. Each year, there are about 110,000 strokes in the UK, 1 million in the European Union and 15 million worldwide. For the NHS, the direct and indirect costs amount to £9 billion. The majority of strokes (~90%) are ischaemic and caused by an occlusion of a brain artery. The possibility to treat stroke exists only for 4.5 hours after symptom onset. Therefore, fast and reliable interpretation of computated tomography (CT) scans is necessary for appropriate identification of patients more likely to benefit from treatment. Brainomix Limited is developing the e-ASPECTS software which can automatically interpret the patients’ brain CT scan. This would help physicians to select patients more likely to benefit for life-saving treatment, whilst excluding those at a high risk of an adverse event. e-ASPECTS automates the clinically validated ASPECTS method which was developed by one of Brainomix’s co-founders. The Alberta Stroke Program Early CT score (ASPECTS) enables a quantitative evaluation of early stroke damage on CT scans. The score assesses the presence of damage within 10 regions of the brain usually affected by a stroke. An ASPECTS score of zero indicates extensive damage, while a normal CT scan is assigned a score of 10. Patients with a low ASPECTS score (less than 5) have a high risk of a bleed within their brain and are unlikely to make an independent recovery, despite treatment. Although the clinical utility of ASPECTS is well established, its clinical use is currently restricted because detection of early damage on CT scans requires extensive experience and expertise, which is not always readily available in an acute setting (especially out-of-hours). Furthermore, manual interpretation of CT scans is associated with significant variability. The e-ASPECTS software offers a solution to these limitations, by automating and implementing the validated ASPECTS method. The benefits of e-ASPECTS are of paramount importance. Introducing e-ASPECTS into clinical practise would be good value for money for the Health Service and would improve the outcome of stroke patients. Acute stroke services would provide the same standard 24/7 as even inexperienced physicians would be able to confidently interpret brain CT scans and accurately select patients more likely to benefit from treatment. Brainomix aims to develop the final version of the e-ASPECTS software in a timely manner so that its benefits are realised for stroke patients both in the UK and worldwide. Overall, e-ASPECTS is a very attractive commercial opportunity. Brainomix is ideally placed to deliver e-ASPECTS to the healthcare market by already having developed and internally validated an algorithm, which can be transformed in a timely manner to a product with all the required certifications. Brainomix will capitalize on the international reputation of its team on the field of stroke to ensure a successful route to market. Licensing e-ASPECTS to European and US hospitals will enhance their stroke treatment, while the growing market of hospitals offering stroke services in developing countries significantly increases the potential return from commercializing e-ASPECTS.

Awaiting Public Project Summary