An AI-empowered blood test was able to more reliably identify ovarian cancer by detecting DNA fragments and protein biomarkers, according to a study published Sept. 30 in the American Association for Cancer Research's journal, Cancer Discovery.
Researchers from Baltimore-based Johns Hopkins Kimmel Cancer Center, in collaboration with academic institutions across the U.S. and Europe, analyzed blood test data from two cohorts of women, a Sept. 30 news release from Johns Hopkins Medicine shared with Becker's said.
Here are five things to know about the study:
- The first cohort of 591 women were treated at hospitals in the Netherlands and Denmark. The second cohort was composed of data from 102 women in the U.S.
- Both cohorts studied results from women with confirmed cases of ovarian cancer, women with benign ovarian tumors and women with no known ovarian growths.
- The biomarkers identified are cancer antigen 125 (CA-125) and human epididymis protein 4 (HE4). The DNA fragments detected are whole-genome, cell-free DNA (cfDNA) fragmentome.
- The blood test, called the DELFI-Pro test, achieved similar detection results across both cohorts:
- In the first cohort, stage 1-4 ovarian cancer cases were detected with a sensitivity of 72%, 69%, 87% and 100%, respectively.
- In the second cohort, the test detected 73% of all cancers and 81% of "high-grade serous ovarian carcinoma," according to the news release.
- In the first cohort, stage 1-4 ovarian cancer cases were detected with a sensitivity of 72%, 69%, 87% and 100%, respectively.
- Using a blood test for ovarian cancer screening may prevent women with benign ovarian growths from having to undergo unnecessary exploratory surgery.