Introducing MI GPSai GPS – Powered by Caris MAIMolecular Artificial Intelligence

Caris has one of the largest and most comprehensive databases of combined molecular and clinical outcomes data in the world, and we are actively employing advanced machine learning capabilities with the database to identify unique molecular signatures. These molecular signatures can be used to better identify cancer subtypes and predict patient response to certain therapies. We are pleased to introduce a tool to help manage cancer of unknown primary (CUP) or cases identified by the ordering physician with atypical clinical presentation or clinical ambiguity.

MI GPSai provides a cancer type similarity assessment that compares the genomic (DNA) and transcriptomic (RNA) characteristics of the patient’s tumor against other tumors in the Caris database (e.g. lung cancer tumor submitted for testing has a similar molecular signature as the lung cancers found in the Caris Database, or conversely the molecular signature is not similar to lung cancer, but similar to another tumor type’s molecular signature).

MI GPSai can be added to any solid tumor order by selecting the appropriate box on the tumor profiling requisition. The result is presented as a prevalence score in a convenient tabular format and is populated onto the final Caris report. These results will provide additional insight by assessing how closely tumors match the genomic and transcriptomic signatures of tissue types to help you make more informed treatment decisions.

– – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – – –

Caris Molecular Artificial Intelligence (MAI) uses the power of DEAN (Deliberation Analytics) and machine learning technology to provide oncologists with the most thorough genomic and transcriptomic classifications to inform decision making. Caris MI AI analyzes historical clinical and outcome data and learns from the past to provide for a better future via molecular subtyping.