AI ‘liquid biopsies’ using cell-free DNA and protein biomarkers could aid early detection of ovarian cancer

A blood test using artificial intelligence (AI) to detect cancer-related genetic changes and protein biomarkers could help screen for early signs of ovarian cancer in women, according to a study by Johns Hopkins researchers Kimmel Cancer Center in collaboration with several other institutions. in the United States and Europe.

The study, published September 30 in the journal Discovery of cancer used AI-based analyzes of DNA fragments and two protein biomarkers to identify women with ovarian cancer.

The two protein biomarkers, called cancer antigen 125 (CA-125) and human epididymal protein 4 (HE4), were previously identified as ovarian cancer biomarkers but, on their own, could not detect reliably ovarian cancer. However, combining these biomarkers with AI-driven detection of cancer-associated DNA fragment patterns in the circulation improved screening accuracy and helped distinguish cancerous tumors from benign tumors.

“Combining artificial intelligence, cell-free DNA fragmentomes, and a pair of protein biomarkers in a simple blood test has improved detection of ovarian cancer, even in patients with single-onset disease. early stage,” says Victor E. Velculescu, MD, Ph.D., senior author of the study, professor of oncology and co-director of the Cancer Genetics and Epigenetics Program at the Johns Hopkins Kimmel Cancer Center. “This AI-based approach has the potential to become an affordable and accessible method for widespread ovarian cancer screening.”

Ovarian cancer is the fifth leading cause of cancer death among women in the United States, with a five-year survival rate of approximately 50%, according to the Centers for Disease Control and Prevention (CDC).

“Early detection of ovarian cancer can save lives, but most women are diagnosed late in the disease course, when survival rates are much lower,” says co-first author Jamie Medina , Ph.D., postdoctoral researcher at Johns Hopkins Kimmel Cancer. Center. “The lack of specific symptoms early in the disease course or effective biomarkers has hampered early detection efforts.”

Investigators previously demonstrated that the AI-powered DELFI (DNA Fragment Evaluation for Early Interception) testing method uses a new approach for liquid biopsies, called fragmentomics, that improves detection of DNA fragments in the blood and effectively detects lung cancer. The technology takes advantage of the fact that DNA, neatly packaged in healthy cells, becomes disorganized in cancer cells.

When healthy cells die and disintegrate, they leave behind a predictable, ordered set of DNA fragments in the blood. However, when cancer cells die and disintegrate, the DNA fragments left behind are irregular and chaotic.

The latest study used blood samples from 94 women with ovarian cancer, 203 women with benign ovarian tumors and 182 women without any known ovarian growths. The study population used to develop the approach included women treated in hospitals in the Netherlands and Denmark. Researchers used the DELFI-Pro test, which combines AI-powered cell-free DNA analysis with tests for CA-125 and HE4, to analyze the samples for ovarian cancer screening.

DELFI-Pro was able to detect significantly more cases of ovarian cancer than tests for either protein alone, with almost no false positives. In fact, it detected 72%, 69%, 87% and 100% of stages I to IV ovarian cancer cases, respectively, while with the same specificity, CA-125 alone detected 34 %, 62%, 63% and 100%. % of ovarian cancers for stages I to IV.

To confirm the results, researchers used the test on a second sample of American women including 40 patients with ovarian cancer, 50 patients with benign ovarian growths, and 22 without known ovarian lesions.

Even in this smaller sample, the test achieved similar success rates, with 73% of all cancers detected and 81% of high-grade serous ovarian carcinomas, the most aggressive form of the disease, with almost no false positives in women without cancer. The DELFI-Pro test was also able to effectively distinguish benign growths from cancerous tumors, something ultrasound exams cannot do.

“Ovarian cancers have a unique signature of DNA fragmentation that is not present in benign lesions,” says Akshaya Annapragada, co-first author and MD/Ph.D. student at Johns Hopkins University School of Medicine.

It is important to be able to distinguish between benign and cancerous ovarian growths because the next step in cancer screening for women with ovarian growths detected by ultrasound is exploratory surgery. The use of ‘liquid biopsy’ tests could save women with benign growths from having to undergo unnecessary surgery.

Velculescu and his colleagues intend to validate the test’s usefulness in larger samples from randomized clinical trials, but he found the current results encouraging. They state: “This study provides additional evidence demonstrating the benefit of genome-wide cell-free DNA fragmentation and artificial intelligence to detect cancers with high accuracy. Our results show that this combined approach has higher screening performance than existing biomarkers.