Caris Life Sciences Publishes Study Showing its Multi-Layer AI-Based Tissue of Origin Predictions are Best-in-Class and Identify when Patients have been Misdiagnosed
Caris GPSai™ utilizes deep learning to significantly improve diagnostic accuracy for cancers of unknown primary and misclassified tumors
This latest advancement marks a shift from traditional machine learning to a deep learning-based approach, enabling more precise prediction of tumor tissue of origin and the identification of potential misdiagnoses during routine molecular profiling, ultimately supporting more informed treatment decisions and potentially improving patient outcomes.
The enhanced Caris GPSai was trained on WES/WTS data from over 200,000 Caris-profiled cases and classifies tumors into 90 categories. The tool demonstrated 95.0% accuracy in identifying tumor tissue of origin in non-CUP cases and successfully reported a tissue of origin in 84.0% of CUP and 96.3% of non-CUP cases during retrospective (N=21,549) and prospective (N=76,271) validations.
"The latest version of GPSai, which is a part of Caris' comprehensive molecular profiling platform, represents a major advancement in precision oncology," said
In clinical use over eight months, GPSai changed the diagnosis in 704 patients, supported by orthogonal evidence such as imaging and molecular markers. These diagnostic shifts impacted treatment eligibility in 86.1% of these cases based on Level 1 clinical evidence, and 53.6% of surveyed physicians reported changing treatment plans as a result, underscoring the potential of GPSai to provide meaningful influence in patient care.
"By enhancing diagnostic accuracy, GPSai empowers physicians to make more informed treatment decisions and identify the tumor type for patients with CUP and those that have been misdiagnosed," said
The publication can be viewed in its entirety on the
About
Caris was founded with the belief and vision that combining a vast set of consistently generated molecular information with robust data-driven insights could realize the potential of precision medicine for patients. Headquartered in
Forward Looking Statements
This press release contains forward-looking statements, within the meaning of the federal securities laws, about
You should not rely upon forward-looking statements as predictions of future events. Although we believe that the expectations reflected in these forward-looking statements are reasonable based on information currently available to us, we cannot guarantee that the future results, discoveries, levels of activity, performance or events and circumstances reflected in forward-looking statements will be achieved or occur. Forward-looking statements involve known and unknown risks and uncertainties, some of which are beyond our control. Risks and uncertainties that could cause our actual results to differ materially from those indicated or implied by the forward-looking statements in this press release include, among other things: developments in the precision oncology industry; future financial performance, results of operations or other operational results or metrics; development, validation and timing of future solutions; the rapidly evolving competitive environment in which we operate; third-party payer reimbursement and coverage decisions; our ability to protect and enhance our intellectual property; regulatory requirements, decisions or approvals (including the timing and conditions thereof) related to our solutions; our compliance with laws and regulations; and our ability to hire and retain key personnel as well as risks, uncertainties, and other factors described in the section titled "Risk Factors" and elsewhere in the prospectus for our initial public offering filed with the
Caris Life Sciences Media:
Corporate Communications
CorpComm@CarisLS.com
214.294.5606
View original content to download multimedia:https://www.prnewswire.com/news-releases/caris-life-sciences-publishes-study-showing-its-multi-layer-ai-based-tissue-of-origin-predictions-are-best-in-class-and-identify-when-patients-have-been-misdiagnosed-302521431.html
SOURCE