NEW YORK, Nov. 13 - Fast, accurate cancer diagnosis? It's gotta be in the blood.
That's the thinking of Correlogic Systems, a Maryland bioinformatics company developing algorithms that can tease apart the differences in plasma proteins between healthy people and people with cancer. With smarter software and the right set of markers, the company hopes diagnosing difficult-to-catch cancers can be possible with a relatively simple and painless blood test.
Less than a year into a Cooperative Research and Development Agreement with researchers at the US Food and Drug Administration and the National Cancer Institute, the group has published two papers describing how its artificial intelligence technique singles out cases of ovarian cancer and prostate cancer.
NCI researchers will begin clinical trials of an ovarian cancer diagnostic in April 2003, and Correlogic hopes to file within the year for a test that can pick out recurrent cancer.
"Right now, we have a Rube Goldberg contraption that absolutely, unequivocally works," said Correlogic CEO Peter Levine. "Now the task is to make this thing work in such a way that lab tech can do it."
A complete version of this article can be seen in next Monday's ProteoMonitor.