A study conducted by researchers at Weill Cornell Medicine, NewYork-Presbyterian, the New York Genome Center (NYGC) and Memorial Sloan Kettering Cancer Center (MSK) found that an artificial intelligence-powered method for detecting tumor DNA in blood has demonstrated exceptional sensitivity in predicting cancer recurrence. This new technology has the potential to significantly improve cancer care by allowing for very early detection of recurrence and close monitoring of tumor response during therapy.
A recent breakthrough in technology has the potential to greatly improve cancer treatment by allowing for extremely early detection of the return of cancer and by closely monitoring how tumors respond to therapy. The findings of this study were published on June 14 in Nature Medicine. The researchers were able to train an artificial intelligence platform, specifically a machine learning model, to identify circulating tumor DNA (ctDNA) from DNA sequencing data obtained from patient blood tests. This method demonstrated high sensitivity and accuracy. The success of this technology was shown in patients with lung cancer, melanoma, breast cancer, colorectal cancer, and precancerous conditions.Ectopic growths in the digestive system.
“Our ability to significantly improve the signal-to-noise ratio allowed us to identify cancer recurrence much earlier than traditional clinical methods, sometimes months or even years in advance,” explained Dr. Dan Landau, one of the authors of the study. He is a professor of medicine specializing in hematology and medical oncology at Weill Cornell Medicine and is also a core faculty member at the New York Genome Center.
The study’s co-first author and co-corresponding author was Dr. Adam Widman, a postdoctoral fellow at the Landau Lab who also specializes in breast cancer oncology at MSK. Other co-first authors included Minita Shah of NYGC and Dr. [Name of other doctor not provided]Amanda Frydendahl from Aarhus University and Daniel Halmos from NYGC and Weill Cornell Medicine have been researching liquid biopsy technology. This technology has had difficulty living up to its potential due to the fact that most methods have only focused on small sets of cancer-related mutations, which are often too scarce in the blood to be reliably detected. As a result, cancer recurrences often go unnoticed. However, Dr. Landau and his team developed an alternative approach using whole-genome sequencing of DNA in blood samples, which allows for more sensitive and logistically simpler detection of cancer signals.– identification of tumor DNA. Since then, this method has been increasingly embraced by developers of liquid biopsies.
In the recent research, the scientists made a significant leap forward by utilizing an advanced machine learning technique (similar to that of ChatGPT and other popular AI applications) to identify subtle patterns in sequencing data — specifically, to distinguish patterns that indicate cancer from those that indicate sequencing errors and other “noise.”
In a trial, the researchers trained their system, known as MRD-EDGE, to detect patient-specific tumor mutations in 15 colorectal cancer patients. After the patients’ surgery andThe use of chemotherapy was able to predict residual cancer in nine patients based on blood data. Later, five of these patients were found to have cancer recurrence using less sensitive methods. However, there were no false negatives, as none of the patients deemed free of tumor DNA by MRD-EDGE experienced recurrence during the study window.
MRD-EDGE also showed similar sensitivity in studies of early-stage lung cancer and triple-negative breast cancer patients, detecting all but one recurrence early and tracking tumor status during treatment.
The researchers demonstrated that MRD-EDGE has the ability to detect evenMutant DNA originating from precancerous colorectal adenomas, which are the polyps that lead to colorectal tumors, have been a subject of study. Dr. Landau, a member of the Sandra and Edward Meyer Cancer Center at Weill Cornell Medicine and a hematologist/oncologist at NewYork-Presbyterian/Weill Cornell Medical Center, expressed the significance of the discovery, stating that it was previously unclear whether these polyps released detectable ctDNA. The research also demonstrated that MRD-EDGE was able to detect responses to immunotherapy in melanoma without prior training on sequencing data from patients’ tumors.lung cancer patients can be detected weeks before with standard X-ray-based imaging. “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,” Dr. Landau said. The research in this story was supported in part by the National Cancer Institute, part of the National Institutes of Health, through grant number R01 CA266619.
