Ovarian cancer is the cause of death for 125,000 women worldwide each year. In the United States, about 15,000 women die each year after suffering from ovarian cancer. One reason for the high death rate is because ovarian cancer is difficult to detect. Often by the time ovarian cancer is diagnosed, it has already progressed to an advanced stage. Researchers have been seeking a routine screening test that could diagnose the disease in its early stages.
Now scientists at the Georgia Institute of Technology have released the results of a new study that used advanced liquid chromatography and mass spectrometry techniques to study blood serum compounds. The researchers then used machine learning computer algorithms to identify 16 metabolite compounds that provided unprecedented accuracy in distinguishing 46 women with early-stage ovarian cancer from a control group of 49 women who did not have the disease.
“People have been looking at proteins for diagnosis of ovarian cancer for a couple of decades, and the results have not been very impressive,” said Facundo Fernández, a professor in Georgia Tech’s School of Chemistry and Biochemistry who led the analytical chemistry part of the research. “We decided to look in a different place for molecules that could potentially provide diagnostic capabilities. It’s one of the places that people had really not studied before.”
The researchers hope to expand the promising results of this study to a much larger group of women, including women from many racial and ethnic groups.
The study, “Highly-Accurate Metabolomic Detection of Early-Stage Ovarian Cancer,” was published on the website of the journal Scientific Reports. It may be accessed here.