Philips receives millions for AI and robotics in stroke treatment

Philips is to receive up to 33.7 million dollars from the US innovation agency ARPA-H to develop new technologies for the treatment of strokes in collaboration with Johns Hopkins University and Boston University. The research focuses on robotics, artificial intelligence and remote endovascular procedures, and aims to improve access to specialist care. The project addresses a global problem, as many stroke patients do not reach a centre capable of performing complex thrombectomies in time.

When treating a stroke, time is of the essence. For patients with a blockage in a major blood vessel, a mechanical thrombectomy can limit or prevent serious damage. A mechanical thrombectomy is a minimally invasive procedure in which a blood clot is removed from a blocked blood vessel.

Not available everywhere

However, this treatment is not available everywhere. In the United States, more than half the population lives more than an hour’s journey from a hospital where the procedure can be carried out. Only a relatively small proportion of patients eligible for a thrombectomy actually receive this treatment.

With funding from the Advanced Research Projects Agency for Health (ARPA-H), Philips aims to develop technology that makes specialised endovascular care less dependent on the physical presence of experts. The project forms part of the Autonomous Interventions and Robotics programme, which promotes research into more autonomous and remotely performed medical interventions.

Philips is collaborating on this with Johns Hopkins University, Boston University and neurosurgeon J Mocco of Weill Cornell Medicine. Among other things, the partners are developing technology for the autonomous navigation of medical devices, steerable catheters, robotic control, procedural guidance based on medical imaging, and the automation of clinical workflows.

Towards remote procedures

In the long term, the new technologies should enable doctors to support or guide parts of an endovascular procedure remotely. Work is also underway on further automation, with medical professionals supervising the system.

In doing so, the research addresses a key bottleneck in healthcare: the concentration of specialist knowledge and facilities. Complex interventions are often restricted to specialist centres, whilst patients with an acute stroke require rapid treatment. By combining robotics, AI and image-guided technology, expertise may in future extend beyond the walls of the hospital where the specialist is physically present.

Integrated intervention suite

The project builds on Philips’ Azurion platform for image-guided interventions. In 2025, we reported on the Azurion neuro biplane system for neurovascular care. The aim is to further integrate various technologies – which currently operate separately – into a single clinical workflow. These include medical imaging, robotic systems, AI-driven automation and smart interventional tools.

According to Philips, the aim is not to replace the doctor, but to make specialist knowledge more scalable. “The aim is not to replace expertise, but to make expertise scalable and accessible,” says Bert van Meurs, Chief Business Leader for Image-Guided Therapy at Philips.

The academic partners are focusing on specific technical areas. Johns Hopkins University is working on autonomous navigation of medical devices. Boston University is developing steerable catheters that can play a key role in robot-assisted endovascular procedures. According to those involved, the main challenge in the coming years will lie in translating these technologies into clinical practice. Robotics and AI must not only function reliably from a technical perspective, but also be safely integrated into existing care processes and be able to operate under medical supervision.

Less dependent on location and capacity

According to Philips, the ARPA-H project thus demonstrates how healthcare innovation is increasingly focusing on the combination of digitalisation, automation and physical medical technology. For stroke care, this development could eventually mean that specialist interventions become less dependent on location and available capacity, provided the technology actually manages to make the transition from the research laboratory to everyday clinical practice.