Researchers have developed a novel tool for calculating and displaying the survival statistics of patients with cancer depending on their genetic profile, which could help practitioners to better track mutation-specific outcomes.
Molecular profiling has become a routine practice in health care, as the identification of biomarkers and specific genomic mutations have been associated with specific cancer mechanisms. Targeting those mutations and mechanisms has been shown to improve outcomes and produce better results for patients. However, the rapid advancement of precision medicine has proved somewhat overwhelming for physicians and practices, necessitating the invention of better tools to evaluate and predict how the molecular pathways of cancer will affect a patient’s health.
-----
Related Content
Precision medicine: Is it realistic?
FDA launches new precision medicine tool
-----
Jeremy Warner, MD, Vanderbilt University (Nashville, TN), along with his colleagues, published data in a recent issue of the Journal of the American Medical Informatics Association detailing the utility of a system they developed called the CUSTOM-SEQ (Continuously Updating System for Tracking Outcome by Mutation to Support Evidence-based Querying) that supports the decision-making of practitioners treating patients with cancer who present with specific gene mutations.
Researchers used a variety of algorithms to extract clinical data from over 4000 patients with cancer and a median follow-up of 17 months. From this patient group, the team found that those who with presented with lung cancer that was positive for the epidermal growth factor receptor (EGFR) mutation had better overall survival than those who did not.
In addition, the researchers also reported on a novel discovery found using the CUSTOM-SEQ system, that guanine nucleotide binding protein, q polypeptide mutations in patients with melanoma correlated with inferior overall survival.
The team also added that, because the data is being continuously updated within the CUSTOM-SEQ system, the evidence base will continue to grow, providing more data for its users. Therefore, they concluded that the tool represents a novel rapid learning system for precision oncology capable of enhancing care for patients and physicians.
