Study: AI Liquid Biopsy Detects Cancer Sooner Than Traditional Methods
Researchers at Weill Cornell Medicine, NewYork-Presbyterian, the New York Genome Center (NYGC), and Memorial Sloan Kettering Cancer Center (MSK) have developed an artificial intelligence (AI)-powered method for detecting tumor DNA in blood. The study, published in Nature Medicine, showed that the AI platform could accurately detect circulating tumor DNA (ctDNA) in patients with various types of cancer, including lung cancer, melanoma, breast cancer, colorectal cancer, and precancerous colorectal polyps.
The researchers trained a machine learning model to analyze DNA sequencing data from patient blood tests, achieving high sensitivity and accuracy in detecting ctDNA. This breakthrough technology has the potential to significantly improve cancer care by enabling the early detection of recurrence and close monitoring of tumor response during therapy.Dr. Dan Landau, a professor of medicine at Weill Cornell Medicine and a core faculty member of the New York Genome Center, stated that the AI platform achieved a remarkable signal-to-noise enhancement. This allowed for the detection of cancer recurrence months or even years before standard clinical methods could do so.
The researchers demonstrated the effectiveness of the AI platform in detecting residual cancer in colorectal cancer patients after surgery and chemotherapy. The platform accurately predicted cancer recurrence in these patients, with no false negatives. Similar results were observed in early-stage lung cancer and triple-negative breast cancer patients, where the AI platform enabled early detection of recurrence and tracking of tumor status during treatment.
The study also found that the AI platform could detect mutant DNA from precancerous colorectal adenomas, suggesting its potential for detecting premalignant lesions. Additionally, the platform showed promise in detecting responses to immunotherapy in melanoma and lung cancer patients, outperforming standard X-ray-based imaging methods.
Dr. Landau emphasized the significance of the AI platform, stating that it addresses a major need in cancer care. The researchers are excited about its potential and are collaborating with industry partners to make it available to patients.The research was supported in part by the National Cancer Institute, a part of the National Institutes of Health, through grant number R01 CA266619.
Sign in with Google