As tumor genetic testing—aka “molecular profiling”—becomes increasingly routine in oncology clinics for treating individual patients, it’s also showing good promise as a broader EHR data-mining environment, advancing the art and science of precision oncology on the whole.
Toward that end, in a study published online March 23 in the Journal of the American Medical Informatics Association, Jeremy Warner, MD, of Vanderbilt University, and colleagues describe how they developed a proof-of-principle tool that can draw from EHR data to automatically calculate and display mutation-specific survival statistics from cancer patients.
With such insights in hand, they were able to overcome the inherent complexity of cancer genomes and, notably, track mutation-specific outcomes.
Using the tool, which the team is calling CUSTOM-SEQ—for Continuously Updating System for Tracking Outcome by Mutation, to Support Evidence-based Querying—they looked at the cases of several thousand Vanderbilt University Medical Center patients who had cancer genotyping.
The team extracted clinical data through a variety of algorithms, refreshing results and sending them to a standard reporting platform. They highlighted significant results for visual cueing and stratified a subset by cancer stage, smoking status and treatment exposure.
Identifying 4,310 patients with a median follow-up of 17 months who had sufficient data for survival calculation, the team found that, as expected, epidermal growth factor receptor (EGFR) mutations in lung cancer correlated with superior overall survival.
This finding validated the CUSTOM-SEQ approach, and the researchers also had a novel finding to add to the precision oncology literature: Guanine nucleotide binding protein (G protein), q polypeptide (GNAQ) mutations in melanoma correlated with inferior overall survival.
From their findings, the authors conclude that CUSTOM-SEQ represents a valid, if novel, rapid learning system for a precision oncology environment.
“Retrospective studies are often limited by study of specific time periods and can lead to incomplete conclusions,” they write. “Because data is continuously updated in CUSTOM-SEQ, the evidence base is constantly growing. Future work will allow users to interactively explore populations by demographics and treatment exposure, in order to further investigate significant mutation-specific signals.”