Rhys Hibbert, a 48-year-old customer services manager from Bedfordshire, has become the world's first patient to undergo brain surgery with real-time artificial intelligence assistance. Surgeons at University College London Hospital successfully removed his tumour, which had begun pressing on his optic nerves and threatened to cause blindness. The operation marks a significant milestone in the application of AI technology to neurosurgery.
Until 18 months before his diagnosis, Hibbert maintained an active lifestyle, walking two miles during his lunch breaks. During one of these walks, he collapsed and began experiencing seizures on the roadside. A subsequent brain scan revealed an 11-millimetre non-cancerous tumour growing on his pituitary gland, a marble-sized organ located at the base of the skull that secretes hormones regulating growth, metabolism, blood pressure and temperature.
The tumour's location presented a surgical challenge. The pituitary gland sits immediately adjacent to the carotid arteries, which supply blood to the brain, and the optic nerves controlling vision. As Hibbert's tumour expanded, it compressed his optic nerves, progressively narrowing his peripheral vision. Beyond the visual symptoms, he experienced severe fatigue and dizziness, causing him to trip frequently.
For 18 years of married life I've always got out of bed and made my wife a cup of coffee, and I wasn't going to let this tumour stop that.
Hibbert acknowledged the emotional and psychological toll of his condition.
Though I had a lot of people kindly offering help, you don't want to be a burden on people,he explained. When surgeons offered him the opportunity to become the first patient to undergo the procedure with their experimental AI system, he accepted without hesitation.
If patients are not prepared to join research how can doctors ever learn and how can medicine ever progress?he said.
How does the AI system work during surgery?
The operation involved inserting an endoscope—a thin camera attached to a rod—through the nose to reach the base of the skull. At this point, the tumour lay close but concealed behind layers of bone and tough membrane. Identifying the safest extraction point proved complex, particularly because anatomical structures vary between individuals. Complication rates for such procedures typically range from 25–50% risk of incomplete tumour removal to 0.5–2% risk of injuring a major blood vessel.
The AI tool addressed these challenges by analysing the live video feed in real time, tracking surgical instruments and marking areas where blood vessels and nerves were most likely to be located. It highlighted zones where tumour removal could be safely performed. The technology functions similarly to facial recognition systems on smartphones, but instead recognises critical anatomical structures that are often hidden from view.
Researchers trained the AI system using hundreds of videos of pituitary tumour removals, carefully annotating vessels and nerves on each recording to enable the system to learn and recognise these vital structures.
It is trained on more operations than most surgeons see or do in a lifetime and can act like an expert second pair of eyes,said Prof Hani Marcus, who helped perform the procedure. According to UCLH, Prof Marcus is a high-volume specialist in minimally invasive endoscopic surgery for pituitary adenomas and related skull base tumours, with such procedures comprising over 95% of his elective surgical work.
Unlike other experimental AI tools in development, this system operates in real time, providing immediate guidance during the procedure. Prof Marcus and Mr Danyal Khan, who carried out the operation at the National Hospital for Neurology and Neurosurgery, emphasised that the AI functions purely as an assistant. The surgeons retain complete control and can override the system's recommendations if they choose to do so.
What was the patient's experience after surgery?
Hibbert's recovery proved dramatic.
When I opened my eyes after the operation it felt like I had got 360-degree vision - I hadn't seen that clearly for a year,he reported. In the eight weeks following surgery, his vision continued improving noticeably every few days. Beyond visual restoration, his energy levels returned to normal and all the side effects he had experienced before the operation disappeared.
It's given me my life back,he reflected on his recovery.
What is the broader context for AI in surgery?
This development occurs within a wider transformation of surgical practice through artificial intelligence and robotic systems. Recent research from Harvard demonstrated that AI outperforms doctors in emergency triage diagnoses and treatment planning, signalling a significant shift in medical technology, though not replacing physicians. Additionally, robotic-assisted surgical procedures have advanced cancer treatment with improved precision and faster patient recovery.
The endoscopic transnasal approach used in Hibbert's surgery represents standard practice for pituitary and central skull base procedures. Surgeons working through the nostrils to reach disease at the skull base have refined this technique over many years. The average UK surgeon performs between 10 and 20 such operations annually, relying on pre-operative scans to familiarise themselves with each patient's unique anatomy.
What are the long-term goals for this technology?
Prof Marcus outlined an ambitious vision for the future of AI in surgery. The team aims to develop what he described as a type of ChatGPT for surgeons—a system that functions as
another expert in the room they can turn to for advice if they want it - or leave if they disagree with it.This approach preserves surgical autonomy while providing access to AI-enhanced decision support.
The project received funding from the National Institute for Health and Care Research and Google. Researchers spent years testing and refining the AI technology in laboratory environments before attempting its first clinical application. The team expressed satisfaction with the initial real-world results and is now preparing a larger clinical trial to evaluate the system's effectiveness across multiple patients and surgical teams.
James Frith, health innovation Minister, welcomed the development.
AI needs proper safeguards and we will always ensure that safety is taken seriously. But we will also ensure we benefit from the opportunities it brings,he stated, acknowledging both the need for caution and the potential benefits of the technology. A 2026 review published in August examined artificial intelligence in pituitary surgery and the path to clinical implementation, reflecting growing academic interest in this emerging field.
Key Facts
- Rhys Hibbert is the first patient worldwide to undergo brain surgery with live AI assistance, successfully having an 11-millimetre pituitary tumour removed
- The AI system analysed video feeds in real time, identifying hidden blood vessels and nerves to guide surgeons toward safe tumour removal
- Hibbert's tumour threatened blindness by compressing his optic nerves; eight weeks after surgery, his vision and energy levels have substantially improved
- The AI was trained on hundreds of pituitary surgery videos, exposing it to more procedures than most surgeons perform in a lifetime
- Surgeons retain full control of the operation; the AI functions as an advisory tool rather than an autonomous system
