OncoSeek® was established using artificial intelligence (AI) to distinguish cancer from non-cancer cases by calculating the probability of cancer (POC) index based on the quantification results of seven protein tumor markers (PTMs) and clinical information including gender and age of the subjects. And prediction the possible affected tissue of origin (TOO) who has been detected with cancer signal.
A large cohort study (nearly 10,000 participants) confirmed that OncoSeek significantly outperformed the conventional clinical method, representing a novel blood-based test for multi-cancer early detection (MCED) which is a non-invasive, easier, efficient, and robust approach. The data showed that the conventional clinical method relied only on a single threshold for each PTM which would make a big problem that was when combining the result of those markers, the false positive rate would accumulate as the number of tests increased. Nevertheless, AI algorithms play a key role in OncoSeek approach, which makes it possible to do multiple cancer screenings based on PTMs. Moreover, this method can accurately trace the origin of cancer which facilitates the follow-up diagnostic workup.