Researchers at King’s College London have demonstrated for the first time that artificial intelligence (AI) can enable a robot to navigate autonomously during a thrombectomy procedure. The study marks a significant step towards wider access to life-saving treatment for strokes.
A thrombectomy is a procedure in which a blood clot is removed from a cerebral artery. This is done via a catheter that is usually inserted through the groin and guided through the vascular system to the brain. The procedure is effective and can significantly reduce mortality and permanent damage.
Complex procedure, limited availability
However, the treatment is not available everywhere, as it requires specialist expertise. Many hospitals lack the necessary knowledge or infrastructure. According to researcher Harry Robertshaw, robotics could change this: “Thanks to autonomous robotics, everyone, wherever they live in the world, could gain equal access to life-saving stroke treatments.” The research has been published in IEEE Robotics and Automation Letters.
AI-driven navigation
The research team developed a robotic system that uses AI to safely guide catheters and guidewires through the complex network of blood vessels. The route from the groin to the brain is long and anatomically challenging.
Instead of using a single algorithm, the researchers opted for a multi-agent approach: multiple AI models, each responsible for a specific part of the journey. This makes the navigation more robust and better adapted to the variation in human anatomy. The technology was tested in both computer models and physical, 3D-printed replicas of human blood vessels. In this experimental setup, the system succeeded in independently following the correct route.
Towards autonomous interventions
According to the researchers, this is the first time an AI system has performed thrombectomy navigation completely autonomously in a physical laboratory environment, outside of simulations. This marks a significant step towards clinical application.
Senior author Thomas Booth emphasises the broader perspective: “By putting these advances into practice, we are one step closer to our goal of improving treatment outcomes for patients by introducing autonomous endovascular procedures into clinical practice.”
Robotics and AI in healthcare
This development is part of a wider trend in which robotics and AI are being used to make specialist care more scalable. In the future, this technology could enable experts to perform procedures remotely, or allow certain parts of procedures to be partially automated.
Although further validation and clinical trials are required, this research demonstrates how AI-driven robotics can contribute to improved access to complex care. This is particularly relevant for time-critical conditions such as stroke, where rapid treatment can make the difference between recovery and permanent damage.
Another British development made the news last year. Healthtech company Cera announced at the time that it had successfully deployed droid-like robots, equipped with AI-driven software, as assistants in home care. The robots are placed in users’ homes and assist them with daily activities. They also collect data on the health and well-being of patients and clients. This data is shared with care team
