How AI-enhanced surgical robotics enables truly personalized surgery

Once ethical and regulatory questions are resolved, the next generation of AI-powered surgical robots could safely enhance medical care, experts write today in Frontiers in Science.

A team of pioneering surgeons and researchers from King’s College London says AI-enhanced surgical robotics could enable “truly personalized surgery”, improving surgical team performance, situational awareness, decision-making and effectiveness.

Their analysis also addresses regulatory questions, such as mitigating risk from systems that continue to learn and change after approval. We are also working on how to prevent biased datasets from increasing inequality, and how to address the concentration of research and industry in resource-rich countries.

Lead author Professor Prokar Dasgupta, a robotic urinary surgeon (formerly of King’s College London and Guy’s Hospital, London), who recently performed the UK’s first long-distance robotic surgery, said: “The use of advanced AI and robotics in the operating room is extremely exciting. Over the next few years, intelligent robots will impact every step of surgery, including technology, emergency response, team roles, workflow and auxiliary functions.”

The authors caution that AI needs to sustain rather than disrupt the operating room and support advancements and refinements in surgical techniques, procedures, and technology. Most importantly, its use should be protected by strong human and regulatory oversight, with the surgeon remaining the primary decision maker.

The promise of AI has significant implications for the continued safe functioning of clinical settings and surgical teams. These will ensure multi-stakeholder discussions to ensure clarity of responsibility, minimization of bias, integration of autonomous robotic systems within surgical teams, global equity, and robust product regulation. ”

Professor Prokar Dasgupta, first author and robotic urological surgeon

Truly customized surgery

Expected advances include AI embedded in surgical robots, known as “embodied AI,” linked to the operating room with sensors that generate spatial understanding, adaptive learning, performance benchmarking, autonomous surgical assistance, and feedback to the team during surgery.

Future surgical AI will also leverage new data streams collected from sensors on the patient, surgical team, and robots to provide real-time guidance and decision support during surgery to optimize surgical procedures.

Predictive AI allows surgeons to accurately visualize the outcome of various actions before taking them (known as cause-and-effect awareness). In the future, this could be used to improve patient outcomes.

Lead author Dr. Alejandro Granados, from King’s College London, said: “Surgery is on the brink of a major transformation, and technology will not only help predict outcomes, but also guide clinicians to the most appropriate and personalized treatment for each patient.”

Adjustment of adaptive system

Currently, regulators approve medical technologies based on submitted forms, but this poses challenges given the ability of surgical robots incorporating AI to learn, adapt, and make post-approval changes.

To address this challenge, the authors call for regulatory reform, including changes to licensing pathways, device classification, post-market surveillance, and compliance standards to better address the high-risk profile of changing systems.

“AI’s ability to learn presents unprecedented challenges,” said Dr. Granados. “We are at a pivotal moment in surgery, and we need to start answering these questions to ensure that patients can reap the rich benefits that an AI-powered operating room has to offer.”

This paper argues that clinical trials should adopt standardized metrics for evaluating AI software, human-AI, and human-robot interactions. It also recommends that regulators work with professional bodies to oversee surgical training as medicine moves from clinical expertise to a data-driven approach.

It also recommends new models of collaboration between academia, industry, and health systems in low-income countries to create cost-effective AI and robotics ecosystems that benefit everyone.

Professor Dasgupta said: “Ensuring the continued safety and effectiveness of robotics and AI in surgery requires a new set of frameworks across regulation and compliance, clinical trial methods, reporting standards and training approaches.”

Dr. Granados said: “Realizing this vision on a global scale will require careful management. We must ensure that healthcare workers and patients around the world can equitably benefit from the exciting potential of upcoming AI and robotics innovations.”

human decision maker

The authors expect future iterations of robotics to operate with ever-higher degrees of autonomy while maintaining essential human oversight.

These describe how the role of the surgeon will move towards supervision, coordination and high-level decision-making, while nurses, anesthetists and assistants can look forward to developing further skills. It is also expected that surgical teams will be complemented by clinical data scientists, as well as AI and robotic integration engineers.

Professor Dasgupta said: “To maintain the clear chain of authority necessary to perform safe surgery, human surgeons need to remain the primary decision makers, and insights from AI models need to be presented differently to members of the surgical team based on their role.”

Dr Granados said: “AI and robotics strategically deployed in the operating room will form the basis of a transition to systems that learn from every surgery, support surgical teams in real time, and provide safer, more accurate and better outcomes for patients.”

“However, we must ensure that human judgment remains central while addressing today’s unmet surgical needs and disparities in who benefits from access.”