A study led by researchers at Weill Cornell Medicine, NewYork-Presbyterian, the New York Genome Center (NYGC) and Memorial Sloan Kettering Cancer Center has shown superior sensitivity in predicting cancer recurrence.

The study used an artificial intelligence (AI) powered method for detecting tumour DNA in blood.

The new AI technology can improve cancer care with the very early detection of recurrence and close monitoring of tumour response during therapy.

In the study, the researchers showed that they could train a machine learning model, a type of artificial intelligence platform, to detect circulating tumour DNA (ctDNA).

The model works based on DNA sequencing data from patient blood tests, with very high sensitivity and accuracy.

The researchers successfully demonstrated the technology in patients with lung cancer, melanoma, breast cancer, colorectal cancer, and precancerous colorectal polyps.

The study co-corresponding author Dan Landau said: “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.

“It had not been clear that these polyps shed detectable ctDNA, so this is a significant advance that could guide future strategies aimed at detecting premalignant lesions.

“On the whole, MRD-EDGE addresses a big need, and we’re excited about its potential and working with industry partners to try to deliver it to patients.”

In the last few years, Landau and colleagues developed an alternative approach based on whole-genome sequencing of DNA in blood samples.

The new approach enabled them to acquire more signals, facilitating more sensitive, and logistically simpler, detection of tumour DNA.

In the new study, the researchers used an advanced machine-learning strategy to detect subtle patterns in sequencing data and to distinguish patterns suggestive of cancer.

They trained the system, dubbed MRD-EDGE, to identify patient-specific tumour mutations in 15 colorectal cancer patients.

The system predicted that nine patients had residual cancer, using their blood data after surgery and chemotherapy.

With less sensitive methods, five of the patients were found to have cancer recurrence.

The MRD-EDGE system returned no false negatives, with no patients deemed free of tumour DNA experiencing recurrence during the study window.

It showed similar sensitivity in studies of early-stage lung cancer and triple-negative breast cancer patients, with early detection and tracking of tumour status during treatment.

The researchers showed that MRD-EDGE can detect even mutant DNA from precancerous colorectal adenomas, the polyps from which colorectal tumours develop.

Furthermore, MRD-EDGE could detect responses to immunotherapy in melanoma and lung cancer patients, weeks before detection with X-ray-based imaging, even without pre-training.