Cancer diagnosis and treatment could get a boost from machine learning
A team of researchers including co-lead author Marina Sharifi, MD, PhD, assistant professor, and senior author Josh Lang, MD, MS, associate professor, both of the Division of Hematology, Medical Oncology and Palliative Care, has published a study in the Annals of Oncology detailing a novel technique of analyzing for cancer.
The new analysis technique uses machine learning algorithms to identify DNA from specific types of cancer that may be floating in the bloodstream, allowing doctors to choose the most effective treatment for a patient. It is also compatible with the liquid biopsy testing already used in cancer clinics in the United States.
“Liquid biopsies are much less invasive than a tissue biopsy — which may even be impossible to do in some cases, depending on where a patient’s tumor is,” notes Dr. Sharifi. “It’s much easier to do them multiple times over the course of a patient’s disease to monitor the status of cancer and its response to treatment.”