Abstract 963P
Background
Hepatocellular carcinoma (HCC) is the third leading cause of cancer-related deaths worldwide. Early detection of HCC is critical for timely treatment and a better prognosis. In this prospective study (ASCEND-Hep, NCT04835675), we aimed to explore multi-omics including cell-free DNA (cfDNA) methylation, mutation, and α-fetoprotein (AFP) in early detection of HCC.
Methods
This multicenter study prospectively collected blood samples from patients with HCC and benign liver diseases. Age-matched non-cancer controls were obtained from a previous study. Methylation and mutation were detected through a methylation panel of 161,984 CpG sites and a cancer-associated 168-gene panel, respectively. Models were developed in a training set (cancer: 172; non-cancer: 206) and tested in a validation set (cancer: 117; non-cancer: 140). Then the locked models were validated in an independent validation set (cancer: 158; non-cancer: 637).
Results
In the training set, cfDNA methylation model had a higher area under curve than AFP and mutation alone (P<0.05). In the validation set, the methylation model yielded an overall sensitivity of 92.3% (95% CI, 85.9%–96.4%) at a specificity of 95.0% (90.0%–98.0%). Meanwhile, AFP >400 ng/mL had a sensitivity of 27.3% (18.8%–37.2%) with a specificity of 100.0% (96.5%–100.0%). Combining cfDNA methylation and AFP showed a better performance with a sensitivity of 94.0% (88.1%–97.6%) and a specificity of 95.0% (90.0%–98.0%), while the addition of mutation did not further improve the performance. Consistent results were observed in the independent validation set that the combined model achieved a sensitivity of 90.5% (84.8%–94.6%) at a specificity of 97.3% (95.8%–98.4%). The sensitivity of the combined model in Barcelona Clinic Liver Cancer Classification 0–A was 87.1% (78.0%–93.4%).
Conclusions
cfDNA methylation yielded superior performance than AFP and mutation alone. Our study highlights a potential clinical utility of combining cfDNA methylation and AFP for HCC early detection.
Clinical trial identification
NCT04835675.
Editorial acknowledgement
Legal entity responsible for the study
The authors.
Funding
Burning Rock Bioengineering Ltd.
Disclosure
All authors have declared no conflicts of interest.
Resources from the same session
842P - Multicenter real-world study of newly diagnosed advanced-stage extranodal natural killer/T cell lymphoma (ENKTL): Proposal for intensive therapy
Presenter: Yu-Ce Wei
Session: Poster session 18
844P - Progression -free survival prediction of multiple myeloma patients in five European countries using machine learning models
Presenter: Maria Luisa Pleguezuelo Witte
Session: Poster session 18
845P - A machine learning based clinical platform for cancer subtyping and data integration in hematological malignancies
Presenter: Michelle Tang
Session: Poster session 18
846P - Artificial intelligence-driven identification of onco-hematology patients who may develop severe COVID-19
Presenter: Souad Assaad
Session: Poster session 18
847P - Fatal infections among leukemia patients
Presenter: Huijie Zhou
Session: Poster session 18
848P - Mortality after rasburicase vs allopurinol anti-hyperuricemia monotherapy in patients with liquid tumors
Presenter: Mitchell Cairo
Session: Poster session 18
849P - Long non-coding RNA signatures and their role in the progression of childhood T cell acute lymphoblastic leukemia
Presenter: Pankaj Sharma
Session: Poster session 18
850P - A zebrafish model of MYC-driven acute myeloid leukemia reveals that neutrophil resistance to oncogenic transformation depends on their ability to promote PP2A-mediated MYC proteasomal degradation
Presenter: Anna Maria Luciano
Session: Poster session 18
851P - Characterization of a zebrafish model of MYC-driven acute myeloid leukemia
Presenter: Anna Maria Luciano
Session: Poster session 18
852P - c-MAF-driven metabolic reprogramming mediates H3K27 hyperacetylation to regulate super enhancer-associated genes
Presenter: Phyllis SY Chong
Session: Poster session 18