World’s First Patient Undergoes Live AI-Assisted Brain Surgery

The world’s first patient to undergo brain surgery with real-time artificial intelligence assistance has successfully had a brain tumour removed, marking a significant step forward for AI-assisted medicine.

Rhys Hibbert, a 48-year-old father of two from Bedfordshire, underwent the pioneering procedure at University College London Hospital. Surgeons said the tumour could eventually have caused him to lose his sight.

Hibbert had previously been fit and healthy, regularly taking two-mile walks during his lunch breaks. About 18 months ago, however, he suddenly lost consciousness and suffered a seizure while walking.

A subsequent brain scan revealed an 11mm benign tumour on his pituitary gland, a small organ located at the base of the brain that produces hormones involved in growth, metabolism and the regulation of blood pressure and body temperature.

The tumour was positioned dangerously close to the carotid arteries, which supply blood to the brain, and the optic nerves responsible for vision. As it grew, it began putting pressure on the optic nerves, reducing Hibbert’s peripheral vision. He also developed severe fatigue, dizziness and problems with coordination.

Although immediate surgery was not initially necessary, doctors eventually offered Hibbert the opportunity to become the first patient to undergo the procedure with the assistance of a specially developed AI system.

“I thought that if patients are not willing to take part in research, how can doctors learn and medicine progress?” he said.

AI acts as an extra pair of expert eyes

The operation was performed through the nose using an endoscope — a thin camera that allows surgeons to reach the base of the skull without making a large external incision.

The tumour was located behind layers of bone and protective membrane, making it difficult to identify the safest route for removal. Its proximity to major blood vessels and nerves increased the risk of complications.

During the procedure, the AI system analysed the live video feed from the operation. It tracked the surgical instruments and highlighted areas where critical blood vessels and nerves were likely to be located, helping surgeons determine where it was safest to remove the tumour.

The technology works in a similar way to facial-recognition systems used by smartphones, but instead of identifying faces, it recognises important anatomical structures that may not be visible to the surgeon.

The AI was trained using hundreds of videos of pituitary tumour operations. Researchers manually identified blood vessels and nerves in the footage, allowing the system to learn how to recognise these structures during surgery.

Professor Hani Marcus, who was involved in the procedure, said the system had been trained on more operations than most surgeons would encounter during their entire careers. He described it as an “expert second pair of eyes”.

Unlike many experimental medical AI systems that analyse scans or surgical footage after an operation, this technology operates in real time.

The researchers stress that the AI does not make decisions independently. Surgeons remain fully in control and can accept or disregard its recommendations.

The team’s long-term goal is to create a kind of “ChatGPT for surgeons” — an AI assistant that could provide expert guidance during complex procedures whenever doctors need an additional source of information.

“It’s given me my life back”

The procedure appears to have had a major impact on Hibbert’s recovery.

“When I opened my eyes after the operation, it felt like I had 360-degree vision,” he said, adding that he had not seen so clearly for around a year.

In the eight weeks following surgery, he noticed his eyesight continuing to improve. His energy levels also returned, while the symptoms he had experienced before the operation disappeared.

“It’s given me my life back,” Hibbert said.

The AI system was developed by researchers at University College London with funding from the UK’s National Institute for Health and Care Research and Google. Following years of laboratory testing, the team is now preparing a larger clinical trial.

The researchers say the successful operation demonstrates how real-time AI could eventually help surgeons navigate some of the most challenging areas of the human body while maintaining human oversight and decision-making.

Follow NEWS.am Medicine on Facebook and Twitter