Dr. James Tudor, MD, spearheads the combination of AI into XCath’s robotics systems. Driven by a passion for the convergence of technology and medicine, he enthusiastically balances his roles as a practicing radiologist, Assistant Professor of Radiology at Baylor College of Medicine, and AI researcher.
Founded in 2017, XCath is a startup focused on advancements in medical robotics, nanorobotics, and materials science. The corporate develops next-generation endovascular robotic systems and steerable guidewires geared toward treating cerebrovascular disorders and other serious medical conditions.
Dr. Tudor, what initially sparked your interest within the intersection of AI and medicine, particularly in the sphere of radiology?
In 2016, as I used to be starting my radiology residency, DeepMind’s AlphaGo defeated world champion Go player Lee Sedol. AlphaGo’s ability to compress and abstract the vast complexities of Go, a game with more possible board positions than atoms within the observable universe, captured my imagination. Enthusiastic about AI’s potential to rework radiology and medicine as an entire, I dove headfirst into AI. During residency, I’d spend my evenings and weekends doing AI projects.
Are you able to tell us more about your journey from medical school to becoming the VP of AI at XCath? What motivated you to pursue AI integration inside healthcare robotics?
My profession path has taken some unexpected turns. After ending my radiology residency, I desired to dedicate more time to AI and its industrial applications. I joined a fitness robotics startup, founded by Eduardo Fonseca, who’s now XCath’s CEO. It was a formative experience, but I never anticipated it could lead down the trail of treating acute stroke with endovascular telerobots.
Around a decade ago, a revolution occurred in acute stroke care. The usual of care was a medicine called tPA that will break up the clot. In 2015, clinical trials demonstrated the prevalence of directly removing the clot from the cerebral arteries by navigating tiny guidewires and catheters inside the arterial vasculature, a procedure called mechanical thrombectomy. Despite the procedure being markedly effective for big vessel strokes, lower than 40% of the US population has access to it. There are a limited variety of stroke centers, generally limited to urban areas, which have specialists who can perform the procedure. Globally, the statistics are much more dismal: lower than 3% of the world has access.
XCath’s mission is to extend access to mechanical thrombectomy with a hub-and-spoke model, where specialists can provide expert stroke care from a distance with endovascular telerobots deployed to regions without access.
Eduardo asked me how AI could augment the protection of the telerobotic system. I used to be so curious I spent a number of weeks deep in research, having conversations with interventionalists and learning concerning the telerobot. The mission and potential humanitarian impact are so compelling I had to reply that decision to arms.
How did your experiences as an educational radiologist shape your approach to integrating AI in medical devices?
Teaching radiology residents has sharpened my ability to clarify complex ideas clearly, which is essential when bridging the gap between AI technology and its real-world use in healthcare. It also keeps me grounded within the challenges clinicians face, which helps me design AI solutions which might be clinically practical and user-friendly.
Because the VP of AI at XCath, what are a number of the key challenges you faced while integrating AI into XCath’s robotic systems? How did you overcome them?
Integrating AI into surgical robotics presents a U-shaped challenge. The best difficulties lie firstly—acquiring and managing data—and at the top—integrating it into an embedded software package. Compared, the actual training of the AI models is comparatively straightforward.
Acquiring medical data is difficult, but fortunately, we were able to determine excellent image-sharing partnerships. Implementing the models for clinical use requires orchestrating the efforts of varied teams, including AI, Quality, Software, UI/UX, and Robotic engineers, all while continuously validating with the clinical team that the answer is helpful and effective. With so many moving parts, success ultimately relies on having dedicated, high-performing teams that communicate often and effectively.
Could you elaborate on how AI enhances the capabilities of XCath’s endovascular robotic systems? What role does AI play in improving patient outcomes?
AI algorithms can function a relentless teacher and assistant, decreasing the cognitive load and leveling up all providers to supply world-class care. AI can provide intraoperative and postoperative feedback, accelerating the training and adoption strategy of endovascular robotics. We aim to make the system so effective and accessible that other intravascular specialists resembling interventional body radiologists and interventional cardiologists might be trained to supply acute stroke care with the robot.
Moreover, locally embedded algorithms can provide an additional level of safety from cyber-attacks and network failures as they anticipate the expected path of a procedure and might alert and pause the procedure within the case of the unexpected.
At the top of the day, we don’t need to take control from the interventionalist, but augment their abilities in order that every patient might be confident they’re getting world-class care.
How does XCath’s AI-driven technology address the complexities of navigating the human vasculature during endovascular procedures?
XCath’s Endovascular Robotic System represents a serious advancement in precision medicine, designed to navigate intricate human vasculature with sub-millimeter accuracy. Our system is designed to reduce procedural variability and enhances control over various endovascular devices through an intuitive control console.
Moreover, XCath’s ElectroSteer Deflectable Guidewire System, the world’s first electronically-controlled steerable smart guidewire, incorporates a steerable tip engineered to navigate complex vascular anatomies and difficult vessel angulations.
AI will further enhance navigation capabilities with locally embedded computer vision and path planning models. These models play an important role in reducing the cognitive load on interventionalists during procedures by assisting with real-time image evaluation and enhancements and providing safeguards through parallel autonomy.
XCath recently achieved a major milestone with the world’s first telerobotic mechanical thrombectomy demonstration. Could you share your insights on the role AI played on this groundbreaking procedure?
We used an earlier version of the robot for that groundbreaking achievement, so AI didn’t play a task. Nonetheless, it’s an incredible milestone that lays the muse for future integration of AI into telerobotic procedures.
On this live demonstration, Dr. Vitor Pereira performed an MT procedure from Abu Dhabi on a simulated patient in South Korea, removing a blood clot within the brain in minutes. We were thrilled by the outcomes of the telerobotic demonstration, which found low latency and reliable connection between the robotic controller positioned in Abu Dhabi and the robotic device in South Korea. We project regional robotic telestroke networks, but we went to an extreme to display the capabilities of the technology.
What do you think is the longer term of telerobotic surgery within the treatment of acute neurovascular conditions, and the way is XCath preparing to guide on this space?
Justifying the need of telerobotic surgery in lots of medical scenarios might be difficult, especially when a surgeon is instantly available or patient transfer is possible. Nonetheless, within the context of stroke treatment, where every minute counts and neurons are rapidly lost, telerobotic interventions change into crucial.
XCath is uniquely positioned to pioneer telerobotic surgery, initially specializing in stroke treatment. Our approach addresses the critical need for rapid intervention in areas with limited access to specialized care. Once we have successfully tackled this challenge, I imagine it’s going to pave the best way for telerobotic solutions in other time-sensitive medical emergencies. Also, given the intense precision of the robotic controls, there may be potential for using the robot locally to perform technically difficult surgeries, resembling aneurysm repairs.
Where do you see the longer term of AI in healthcare heading, particularly in relation to robotic systems and minimally invasive procedures?
AI has immense potential to revolutionize healthcare. The initial wave of AI applications has primarily focused on triage and efficiency improvements. We have seen significant advancements in radiology, particularly in flagging urgent cases or automating acquisition of measurements. I’m also enthusiastic about automated medical record documentation. A current challenge is that doctors often spend more time documenting in front of computers than interacting with patients. I anticipate the event of systems that may document patient interactions or surgeries in real-time, freeing up useful physician time. Within the realm of robotics, AI will play an important role in assisting and proctoring, thereby enhancing the consistency and quality of care.
Within the foreseeable future, AI goes to reinforce, but not replace surgeons. The implementation of parallel autonomy in robotic systems will significantly improve each the protection and efficiency of procedures.
As someone deeply involved in AI research, what advancements in AI do you think that could have probably the most significant impact on medical device development over the subsequent decade?
In the previous couple of years, we have witnessed a wave of supervised deep learning models receiving FDA approval and are only now starting to satisfy their promise of reworking healthcare. A wave of generative AI applications will likely dominate the subsequent few years. Agentic AI, by comparison, is in its infancy, but holds much greater promise. As AI is rapidly evolving, it’s totally likely we’ll see multi-agent systems that may diagnose and treat in real time. There will likely be additional regulatory hurdles for these agents whose actions are each opaque and probabilistic. Nonetheless, global need will drive the demand for adoption. In Rwanda, the corporate Zipline is using flying drones to deliver vital medical supplies inside minutes across the country. Similarly, in places that lack access to medical resources, the danger/profit equation could be very different and would likely prompt them to leapfrog the developed world within the deployment of multi-agentic AI medical devices.
