The AI-powered blood test developed at top Scottish university that detects breast cancer early

A new AI-powered blood test is the first to detect signs of breast cancer in its earliest stages when it is “far more easily treated”, Scottish scientists have announced.

The new fast and non-invasive test works by revealing the subtle changes in the bloodstream that occur at the initial “1a” stage of the disease.

Researchers at the University of Edinburgh, who carried out the study, said these early indicators of the disease are not detectable using existing techniques.

Artificial intelligence is being used to better detect breast cancer. Picture: PA

Standard tests for breast cancer involve a physical examination, X-ray, ultrasound scans, or an analysis of a sample of breast tissue known as a biopsy, with early detection strategies relying on screening people based on their age and whether they are in at-risk groups.

The researchers said the new technique, which combines a laser analysis technique known as “Raman spectroscopy” and a form of AI called machine learning, enabled them to spot the disease at the earliest stage for the first time.

Campaigners described the pilot study as “exciting”.

Dr Simon Vincent, director of research, support and influencing at Breast Cancer Now, said: “Detecting and diagnosing breast cancer early means patients are far more likely to survive the disease, and with over 55,000 people being diagnosed with breast cancer every year in the UK – and 11,000 sadly dying from the illness – any research looking at how we can better detect breast cancer is urgently needed.”

Dr Vincent added: “While further research is needed, this exciting pilot study, which used tissue samples from Breast Cancer Now's Biobank, shows how innovative AI technology could be harnessed to improve early detection of breast cancer and ensure people can begin treatment as quickly as possible, when it will be most effective.”

The new test involves first shining a laser beam into blood plasma taken from patients.

The properties of the light after it interacts with the blood are then analysed using a device called a spectrometer to reveal tiny changes in the chemical make-up of cells and tissues, which are early indicators of disease.

A machine-learning algorithm is then used to interpret the results, identifying similar features and helping to classify samples.

A pilot study using samples from 12 breast cancer patients and 12 healthy patients showed the technique was 98 per cent effective at identifying breast cancer at stage 1a.

The study also showed the test could distinguish between each of the four main types of breast cancer with 90 per cent accuracy, which the researchers said could enable patients to receive more effective, personalised treatment.

The study team said implementing the new technique as a screening test would help identify more people in the earliest stages of breast cancer and so improve the chances of treatment being successful.

Study lead Dr Andy Downes, of the University of Edinburgh’s school of engineering, said: “Most deaths from cancer occur following a late-stage diagnosis after symptoms become apparent, so a future screening test for multiple cancer types could find these at a stage where they can be far more easily treated.

“Early diagnosis is key to long-term survival, and we finally have the technology required.

“We just need to apply it to other cancer types and build up a database before this can be used as a multi-cancer test.”

The study team said the new method could pave the way for a screening test for multiple forms of cancer, and they aim to expand the work to involve more participants and include tests for early forms of other cancer types.

They said similar approaches had been trialled to screen for other types of cancer in the past, but the earliest they had been able to detect disease was at stage two.

The study, which was published in the Journal of Biophotonics, also involved researchers from the University of Aberdeen, the Rhine-Waal University of Applied Sciences and the Graduate School for Applied Research in North Rhine-Westphalia.