Bradford skin cancer waiting times cut by new AI technology

The clinic using AI to detect skin cancer earlier

BBC

Staff at an NHS clinic using artificial intelligence (AI) to detect skin cancer sooner have said the technology could be a “game changer”.

The dermatology team at St Luke’s Hospital in Bradford adopted the new system in April to examine suspicious skin lesions.

The quick scanning means that 32 patients can be seen in each session, compared to 24 before AI was introduced.

Consultant plastic surgeon Mr Zakir Shariff said the technology has had a “big impact” on waiting times and the number of unnecessary procedures.

The AI system is called DERM, which stands for Deep Ensemble for the Recognition of Malignancy.

The company behind the technology, Skin Analytics, claims the AI is 99.9% accurate at ruling out melanoma cases.

A healthcare assistant takes three photographs of the suspicious mole or lesion and then uploads them to the system, which analyses them in minutes.

Patients with benign cases are offered advice and discharged, while those identified as suspicious are referred to a specialist as part of a one-stop clinic.

In Bradford, every image is double-checked by a clinician to make sure the diagnosis is correct.

“This has had a big impact on all the bottlenecks – right from waiting times for patients to unnecessary investigations being done and to being seen by a clinician,” Shariff said.

“It’s amazing, I mean it’s excellent, at giving non-cancerous diagnosis quite quickly, within minutes.

“It’s had an impact for patients and for the department.”

The number of unnecessary biopsies has dropped by about 10% since the AI was introduced, according to the trust.

Lawrence Patten was urgently referred to the clinic by his GP because of a suspicious mole on his back.

The 73-year-old has multiple myeloma and a previous history of skin cancer on his right forearm, known as squamous cell carcinoma.

Images of his mole were flagged as suspicious by the AI but a subsequent examination by a specialist doctor suggested it was likely benign.

The mole will be removed and tested to confirm the diagnosis.

Patten, a former builder, said he was pleased to have been seen so promptly.

“It’s very good news,” he said. “It’s not ticking away in my mind, which is one of the biggest things with cancer.

“The sooner they find things, the quicker they can sort it.”

Dr Nader Ghaderi, an associate specialist in dermatology, who examined Patten, said the AI was right to flag his case.

“If he was not checked by AI and was checked by a doctor, the doctor would have done a biopsy or definitely a follow-up would have been arranged; although the findings are pointing towards a benign lesion,” he said.

The AI technology has been recommended by the National Institute for Health and Care Excellence for use in the NHS for the next three years, while evidence is collected.

It is now deployed in 40 NHS hospital trusts and Bradford Teaching Hospitals was the first in Yorkshire to adopt it.

Tom White, the trust’s general manager who oversees dermatology, said early evidence suggested the use of AI could be a “game changer”.

“It will significantly reduce the number of urgent referrals that require review by dermatologists, reducing waiting times and allowing us to concentrate on the most urgent cases,” he said.

There are around 5,000 referrals every year for suspected skin cancer in Bradford, according to the Trust.

However, only about 8%, or 400 patients, are found to have malignant cancer.

Listen to highlights fromWest Yorkshire on BBC Sounds, catch up with the latestepisode of Look North.

More on this story

Medical technology
Skin cancer
Artificial intelligence
NHS
Bradford