A new AI technology being trialled at a major NHS hospital trust could transform treatment for diabetes patients by significantly reducing the need for limb and foot amputations.

Barts Health NHS trust – which runs five hospitals in east and central London – has been testing Clinithink’s artificial intelligence software for the past three years, using it to analyse 14.2 million medical records and notes to identify patients with diabetic foot disease (DFD).

The system could save thousands of patients from having their limbs or feet amputated, marking a “world-changing” shift in how patients with complicated conditions such as diabetes are treated.

Using the software, called CLiX unlock, it identified 61,756 patients with diabetes – 3,119 of whom had diabetic foot disease – from Barts’ patient records in a matter of weeks. The task would have taken a single clinician more than 100 years to complete, helping clinicians schedule earlier treatment that could help to avoid amputations further down the line.

“Attempting this scale of analysis manually would have been frankly impossible,” said Dr Charles Gutteridge, Chief Clinical Information Officer at Barts Health. “Theoretically it would have taken one clinician over a hundred years to review that volume of documents. So not only does AI technology help us find patients who we couldn’t otherwise find, it also saves precious clinical time. This is a first and most important step in being able to treat many patients earlier than would have been possible using a manual process to find them and preventing the serious complications that may result in amputation.”

In the next phase of work planned by the Barts Health team, the characteristics extracted by the software in the cohort it identified, along with input from other sources, will be used to determine whether this approach can predict which patients are most likely to develop the severe complications associated with Diabetic Foot Disease.

Mr Sandip Sarkar, Consultant Vascular Surgeon at Barts Health and lead clinician for the project, added: “Using this advanced AI technology, we are very excited about the possibility of being able to predict which patients are most likely to experience the worst consequences of DFD.

“This will enable us to focus our precious clinical resource on those patients likely to benefit most from early intervention, which will also reduce the burden on hard-pressed acute services. This is how we need to manage chronic disease in the post-Covid era.”

As diabetic patients often also experience issues with their eyes, hearts and kidneys, treating DFD usually involves having to consult with specialists from a number different backgrounds, including diabetologists, heart and kidney experts, podiatrists and vascular surgeons, said Sarkar. “This software allows me to type a note and it will trawl through records and say, ‘We’ve found that if you adjust the blood pressure of a patient in exactly the same situation by X, it increases their longevity by Y per cent.’”

He thinks the new system could help to save tens of thousands of diabetic patients from future amputations.

“Worldwide, a leg is amputated from a diabetic patient every 20 seconds, that’s the scale of this problem. This is the most promising software that I’ve ever seen, and I’d like to help more than the 3,119 people from this project – I’d like to commit to helping tenfold that, just in east London.”

Dr Sarkar carried out the project with Dr Charles Gutteridge, chief clinical information officer at Barts Health, and data analyst Dr Sophie Williams.

The software could easily be applied to other multi-faceted health conditions, including chronic obstructive airways disease, which affects the heart as well as the lungs, or even elderly care, Dr Sarkar said.

The team now hopes to be able to access electronic records for primary healthcare in north-east and east London, as more data means higher accuracy.

“I wouldn’t be surprised at all if it’s borrowed and mirrored for what we do nationally and internationally,” he added. “This is world-changing because almost everything we do in complex medicine is based on individual experience rather than us knowing what to do.

“This will change that to bespoke evidenced medicine and that will be absolutely brilliant and will change the way we do medicine, because it allows us to consider what has previously happened to patients when experts make those interventions.”