Ovarian cancer is the eighth most-common cancer among women globally, and the eighth most-common cause of death from cancer worldwide. In the United States alone, in 2023, there were nearly 20,000 new cases of the cancer, and about 13,270 deaths from the disease. Ovarian cancer is largely asymptomatic prior to metastasis, and there is no early screening detection test. Now, the results from a retrospective study may provide a new method for population-wide ovarian cancer screening.
The study by Medina et al was presented at the American Association for Cancer Research (AACR) Annual Meeting 2024 (Abstract 6086/12). It evaluated a blood-based machine learning assay that combines cell-free DNA (cfDNA) fragmentomes and protein biomarkers, which the investigators found was able to differentiate patients with ovarian cancer from healthy controls at a specificity of over 99% and noninvasively recognize benign masses from malignant ones with an area under the curve (AUC) of 0.87.
The findings demonstrate the power of genome-wide cfDNA fragmentation and machine learning to detect ovarian cancer with high performance, potentially enabling a new paradigm for population-wide ovarian cancer screening and clinical diagnostic utility, according to the study authors.
Study Methodology
The researchers analyzed the efficacy of cfDNA fragmentomes and protein biomarkers in detecting ovarian cancer from plasma of 541 women: 134 with ovarian cancer, 204 without cancer, and 203 with benign adnexal masses. Low-coverage (1–2x) whole-genome sequencing of cfDNA and protein concentrations of CA125 (cancer antigen 125) and HE4 (human epididymis protein 4) were assessed in the same blood samples of each individual.
The researchers developed a classifier using a combined fragmentomic-proteomic machine-learning model incorporating cfDNA fragmentomes using DELFI (DNA evaluation of fragments for early interception) and protein (CA125 and HE4) features. This approach was evaluated for the detection of cancer in two clinical settings: screening for detection of cancers among a healthy population, and the diagnostic setting for classification of adnexal masses as benign or cancerous. They then assessed performance by cross-validation (n = 318 for screening, n = 317 for diagnostic), and externally validated the locked screening model using samples from a separate institution.
Results
The researchers found in the screening setting, the combined approach detected ovarian cancer with a high specificity of > 99% and a sensitivity of 69%, 76%, 85%, and 100% for stage I to IV disease, respectively (AUC = 0.97, 95% confidence interval [CI] = 0.94–0.99). At the same specificity, CA125 alone detected 40%, 66%, 62%, and 100% of ovarian cancers for stage I to IV disease, highlighting the benefit of combining fragmentomic and proteomic features (P = .0009, two-sided test of equal proportions). Analysis of high-grade serous ovarian cancers (n = 10, 9, 24, 3 for stage I to IV disease, respectively) using the novel approach identified 91% of cases at > 99% specificity.
In an external set of cancer samples (n = 20), using the locked screening model and a fixed-score threshold, the approach detected 65% of ovarian cancers. In the diagnostic setting, the approach differentiated benign masses from ovarian cancers with an AUC of 0.87 (95% CI = 0.83–0.91), detecting 60% of ovarian cancers at a specificity of 95%. In the preoperative setting, in which lower specificity is acceptable, this approach may improve management of adnexal masses, according to the researchers.
“We demonstrate the utility of combining cfDNA fragmentomes and proteins for noninvasive detection of ovarian cancer. This approach detects ovarian cancers with high performance, potentially enabling a new paradigm for population-wide ovarian cancer screening and clinical diagnostic utility,” concluded the study authors.
Clinical Significance
“The lack of efficient screening tools, combined with the asymptomatic development of ovarian cancer, contributes to late diagnoses when effective treatment options are limited,” said Jamie Medina, PhD, a postdoctoral fellow at the Sidney Kimmel Comprehensive Cancer Center at Johns Hopkins Medicine and first author of this study. “A cost-effective, accessible detection approach could change clinical paradigms of ovarian cancer screening and potentially save lives.”
The researchers intend to validate their models in larger cohorts of patients to strengthen the associations they observed in this study.
Disclosure: Funding for this study was provided by the Dr. Miriam and Sheldon G. Adelson Medical Research Foundation, Stand Up To Cancer, the Gray Foundation, The Honorable Tina Brozman Foundation, the Commonwealth Foundation, The Mark Foundation for Cancer Research, the COLE Foundation, Delfi Diagnostics, and the National Institutes of Health. For full disclosures of the study authors, visit abstractsonline.com.
