AI Case Study
Stanford University Parker Institute for Cancer Immunotherapy predict childhood leukemia patients relapse with 85% accuracy using machine learning
Stanford University Parker Institute Cancer Immunotherapy analysed wanted to better understand whether they could predict the 10 - 20% of pediatric acute lymphoblastic leukemia patients who would relapse after initial cancer treatment. Research suggests that relapse may be driven by a few treatment-resistant cells that are present during initial treatment. Using machine learning trained on data from 60 children with lekukemia researchers identified six features of leukemia cells that could help predict relapse. The prediction with 85% accuracy was a significant improvement over existing methods.
Public And Social Sector
Education And Academia
"Researchers analyzed samples from 60 children with pediatric acute lymphoblastic leukemia and compared them to samples from healthy patients. Using single-cell mass cytometry (also called CyTOF), the team looked at 35 proteins involved in B-cell development. Applying machine learning to that data, researchers identified six features of leukemia cells that could help predict relapse after treatment.
"The research points to a way that would allow greater personalization in treatment for these pediatric cancer patients."
"The method, used at the time of diagnosis, predicts which patients will relapse with 85 percent accuracy – a significant improvement over the traditional method."
"Machine learning identified six features of expanded leukemic populations that were sufficient to predict patient relapse at diagnosis."
R And D
Core Research And Development
"Pediatric acute lymphoblastic leukemia (ALL) is the most common childhood cancer, diagnosed in about 3,000 American children per year. The study focused on the most common type called B-cell precursor ALL. The majority of these cases are cured with chemotherapy, but 10 to 20 percent of patients relapse. "
"Prior research strongly suggested that cancer relapse may be driven by a few treatment-resistant cells that are present from the beginning of the diseases. The question is could those be identified and treated."
"The researchers tested bone marrow samples taken from 60 all patients at the time of their diagnosis. Each patient had three to 15 years of follow-up medical records available for analysis, including relapse information."