Researchers led by Johns Hopkins have developed an AI-powered blood test that significantly enhances the early detection of ovarian cancer, potentially saving thousands of lives by catching the disease in its initial stages.
A groundbreaking study from the Johns Hopkins Kimmel Cancer Center, in collaboration with institutions across the United States and Europe, has unveiled a new AI-driven blood test that could revolutionize the early detection of ovarian cancer. This promising technology utilizes artificial intelligence to assess cell-free DNA fragment patterns and protein biomarkers in blood samples, significantly improving the accuracy of ovarian cancer screening.
Published on Sept. 30th in the journal Cancer Discovery, the study highlights the potential of combining cancer antigen 125 (CA-125) and human epididymis protein 4 (HE4) biomarkers with AI-based DNA analysis. Traditional methods using these protein biomarkers alone have struggled with reliability, but this innovative approach has shown robust results in identifying cancerous tumors, even at early stages.
“The combination of artificial intelligence, cell-free DNA fragmentomes and a pair of protein biomarkers in a simple blood test improved detection of ovarian cancer even in patients with early-stage disease,” senior author Victor E. Velculescu, a professor of oncology and co-director of the Cancer Genetics and Epigenetics Program at the Johns Hopkins Kimmel Cancer Center, said in a news release. “This AI-enabled approach has the potential to be an affordable, accessible method for widespread screening for ovarian cancer.”
Ovarian cancer is a significant health issue as it is the fifth most common cause of cancer deaths 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). One of the major challenges in reducing these fatalities is the disease’s tendency to be diagnosed in its later stages, where survival rates drop dramatically.
“Early detection of ovarian cancer may save lives but most women are diagnosed late in the course of the disease when survival rates are much lower,” co-first author Jamie Medina, a postdoctoral fellow at Johns Hopkins Kimmel Cancer Center, said in the news release. “The lack of specific symptoms early in the course of the disease or effective biomarkers has hindered earlier detection efforts.”
Previous research by the team showcased the effectiveness of the AI-powered DELFI (DNA Evaluation of Fragments for early Interception) test in detecting lung cancer by analyzing disorganized DNA fragments left behind by dying cancer cells.
The latest study extended this approach to ovarian cancer, analyzing blood samples from over 479 women from hospitals in the Netherlands and Denmark using the DELFI-Pro test, which integrates AI-driven DNA analysis with CA-125 and HE4 protein tests.
The results were compelling. The DELFI-Pro test detected 72% of ovarian cancer cases at stage I, 69% at stage II, 87% at stage III and 100% at stage IV, outperforming the CA-125 alone.
Even in a smaller validation sample from the United States, the test maintained its high detection rates with minimal false positives.
Crucially, it also distinguished between benign and malignant tumors, a capability that standard ultrasound exams lack.
“Ovarian cancers have a unique DNA fragmentation signature that is not present in benign lesions,” added co-first author Akshaya Annapragada, a medical and doctoral student at Johns Hopkins University School of Medicin.
This distinction is vital for sparing patients from unnecessary surgeries resulting from benign growths detected by ultrasounds.
While the results to date are promising, Velculescu and his team plan to validate the test’s utility further through larger clinical trials.
“This study provides further evidence demonstrating the benefit of genome-wide, cell-free DNA fragmentation and artificial intelligence to detect cancers with high accuracy,” Velculescu added. “Our results show that this combined approach has higher performance for screening than existing biomarkers.”
The groundbreaking research has the backing of numerous major foundations and institutions, enabling it to push the boundaries of cancer detection and prevention. With ongoing research and validation, this AI-enhanced blood test could soon become a vital tool in early ovarian cancer screening, potentially saving thousands of lives through earlier intervention and treatment.