NHS turns to AI to cut cancer treatment times

Artificial intelligence can assess where to direct radiotherapy with 90% accuracy faster than a skilled doctor, researchers claim
OSAIRIS in action
OSAIRIS examines cancer patients’ scans to calculate where radiotherapy beams should be directed
Microsoft
Alan Martin27 June 2023

NHS trusts in England will be offered potentially game-changing artificial intelligence to help speed up cancer treatment.

OSAIRIS was developed by researchers at Addenbrooke’s Hospital in Cambridge in collaboration with Microsoft. It examines cancer patients’ scans to calculate where radiotherapy beams should be directed and ensure healthy organs are protected.

For humans, it’s a skilled and painstaking process, taking trained doctors between 20 minutes and three hours to perform for each patient. The same specialists working with artificial intelligence can do it about two and a half times faster, the researchers say.

With the AI boasting a 90% accuracy rate, the doctors give a second opinion, rather than undertaking the main bulk of the work themselves, freeing up their valuable time and reducing waiting times for patients. Researchers say that the scans go unamended around two-thirds of the time.

“OSAIRIS does much of the work in the background so that when the oncologist sits down to start planning treatment, most of the heavy lifting is done,” says Dr. Raj Jena, an oncologist at the Cambridge Universities Hospital NHS Foundation Trust, who led the research.

For cancer patients, the importance of this accuracy can’t be overstated, as protecting healthy organs from radiation is imperative to quality of life, post-treatment. If treatment is targeting the prostate, for example, avoiding damaging the nearby bladder and rectum is important to avoid continence issues going forward.

“That can get so bad that a patient’s life becomes dominated by that,” Dr. Jena told BBC Newsnight. “I know patients where they’ve got a map of the cities that they’re going to, so they know where all the loos are.”

Medical advancement is one of the most exciting fields in artificial intelligence, and while this particular use is for speeding up work and freeing up professionals’ time, other implementations rely on AI’s ability to spot trends that may go unnoticed by human eyes.

An AI trained to tell the difference between cardiomyopathy and constrictive pericarditis, for example, was able to achieve a success rate of up to 96% in two months, while trained doctors were hovering around 56%.

Create a FREE account to continue reading

eros

Registration is a free and easy way to support our journalism.

Join our community where you can: comment on stories; sign up to newsletters; enter competitions and access content on our app.

Your email address

Must be at least 6 characters, include an upper and lower case character and a number

You must be at least 18 years old to create an account

* Required fields

Already have an account? SIGN IN

By clicking Create Account you confirm that your data has been entered correctly and you have read and agree to our Terms of use , Cookie policy and Privacy policy .

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged in