New test detects cancer ‘years’ earlier

Man in lab testing blood. | Newsreel
A new blood testing method has the potential to improve cancer detection. | Photo: Sanjeri (IStock)

A blood testing method, enhanced by artificial intelligence, has the potential to improve current methods of predicting cancer recurrence “by years”.

A study published in Nature Medicine detailed an AI-artificial powered method for detecting tumour DNA in blood, which was showing “unprecedented sensitivity”.

Co-author Dan Landau of Weill Cornell Medicine said the new technology had the potential to improve cancer care with the very early detection of recurrence and close monitoring of tumour response during therapy.

Dr Landau said researchers showed they could train a machine learning model to detect circulating tumour DNA (ctDNA) based on DNA sequencing data from patient blood tests, with very high sensitivity and accuracy.

He said they made successful demonstrations of the technology in patients with lung cancer, melanoma, breast cancer, colorectal cancer and precancerous colorectal polyps.

“We were able to achieve a remarkable signal-to-noise enhancement, and this enabled us, for example, to detect cancer recurrence months or even years before standard clinical methods did so,” Dr Landau said.

Read the full study