We are about to witness a new race in diagnostic testing. Two companies, Ciphergen and Correlogic, are championing similar but competing methods of testing blood proteins for cancer.
The first step is to use a mass spectrometer to identify a protein profile in the blood. The complex pattern produced by the spectrometer has until recently proved impractical for cancer diagnosis. There was just too much information to process. But now, both Ciphergen and Correlogic hope to extract useful information from this data by applying pattern recognition algorithms borrowed from AI research.
[The Correlogic test] correctly identified 50 out of 50 women with cancer and correctly scored negative for 63 out of 66 unaffected women. Later given the name OvaCheck, it promised to be the first blood test accurate enough to be used for general ovarian-cancer screening…
Meanwhile, Wright's group [Ciphergen] in Virginia was also pushing ahead. Using a different algorithm, Wright and Eastern Virginia molecular biologist John Semmes showed that a protein pattern could distinguish prostate cancer from a common noncancerous condition, benign prostatic hypertrophy, in 25 out of 30 cases. The PSA test [the current state of the art], by contrast, is unable to distinguish the two conditions.
The goal is early detection. If a routine blood test can diagnose cancer while it is in its earliest stages, cancer survival rates could skyrocket.Posted by Stephen Gordon at August 3, 2004 02:52 PM | TrackBack