IBM's Watson for Genomics, a cognitive computing platform that suggests potential therapies based on genomic tumor data, can effectively identify patients for new clinical trials, according to recent research out of Chapel Hill-based University of North Carolina Lineberger Comprehensive Cancer Center and IBM Watson Health.
The study, published in the journal The Oncologist, assessed how the Watson for Genomics platform stacked up against a panel of UNC Lineberger cancer experts when tasked with identifying therapeutic options to address tumors with genetic abnormalities. The team assessed Watson for Genomics' performance on next-generation sequencing data from 1,018 cancer cases to complete their analysis.
The board of molecular tumor experts identified actionable genetic alterations in 703 cases, which Watson for Genomics confirmed. The IBM platform also identified potential therapeutic options in an additional 323 patients. Of these 323 cases, 96 had not previously been identified as having an actionable mutation, based on the board's review. Watson for Genomics identified a new clinical trial for most of these cases.
"Our findings, while preliminary, demonstrate that cognitive computing might have a role in identifying more therapeutic options for cancer patients," said William Kim, MD, the study's corresponding author and an associate professor of medicine and genetics at the UNC School of Medicine. "The major finding is that cognitive computing augmented the molecular tumor board process for the interpretation and collection of information regarding a patient's genomic profile."