A new study suggests that IBM’s Artificial Intelligence (AI) Watson may well be a very useful tool for identifying possible therapeutic options for cancer patients.
The study was led by the University of North Carolina Lineberger Comprehensive Cancer Center and focused on the identification of possible treatment options based on the genetics of the patient’s tumor.
To achieve this, Watson for Genomics was used to trawl through a large amount of information from both databases and studies. This was combined with the genetic information of patients, with the intention of flagging up potential treatment plans or clinical trials for 1018 patients who had “tumors with specific genetic abnormalities.”
The study, titled ‘Enhancing next-generation sequencing-guided cancer care through cognitive computing’ was published in The Oncologist on November 20. The background to the study was given as:
“Using next-generation sequencing (NGS) to guide cancer therapy has created challenges in analyzing and reporting large volumes of genomic data to patients and caregivers. Specifically, providing current, accurate information on newly approved therapies and open clinical trials requires considerable manual curation performed mainly by human “molecular tumor boards” (MTBs). The purpose of this study was to determine the utility of cognitive computing as performed by Watson for Genomics (WfG) compared with a human MTB.”
The MTB identified 703 cases which had actionable genetic alterations, which were all backed up by Watson for Genomics. In addition to this though, Watson for Genomics also identified possible treatment options for another 323 patients who hadn’t been flagged up by the MTB. 96 of these had not been identified before as having an actionable mutation.
Of using Watson for Genomics as part of an action plan for patients, William Kim, co-author of the paper said: “Our findings, while preliminary, demonstrate that cognitive computing might have a role in identifying more therapeutic options for cancer patients. I can tell you that as a practicing oncologist, it’s very reassuring for patients to know that we’re able to explore all possible options for them in a very systematic manner.”
This study was very much theoretical in nature – because retrospective data was used, the majority of patients had either already received the all clear from the physicians, or had died. But, for 47 of the patients who were still suffering from active cancer, the findings of Watson for Genomics were forwarded to their physicians.
UNC Lineberger's William Kim, MD, and colleagues report that cognitive computing can scour large volumes of scientific data to identify potentially relevant cancer clinical trials or therapeutic options.
It looks as though that as the amount of treatment options, genomic sequencing and therapeutic options for cancer patients continues to grow apace, utilizing AI will become more commonplace as a rapid option for identifying treatment pathways for patients.
Kim said that: “To my knowledge, this is the first published examination of the utility of cognitive computing in precision cancer care.” We’re sure there will be many more, and certainly that will only benefit patients.
Top image: Cancer Cells. (CC BY-SA 4.0)