On June 5, 2024 GC Genome Corporation, a leading diagnostics company, reported new data from its AI-based liquid biopsy platform for non-invasive colorectal cancer (CRC) detection at the 2024 American Society of Clinical Oncology (ASCO) (Free ASCO Whitepaper) Annual Meeting (Press release, GC Genome, JUN 5, 2024, View Source [SID1234644150]). Conducted in collaboration with Genece Health Inc., a strategic partner based in San Diego, the study demonstrated significant promise for accurate non-invasive CRC and advanced adenoma (AA) detection by analyzing cell-free DNA (cfDNA) whole genome sequencing (WGS) data.
Schedule your 30 min Free 1stOncology Demo!
Discover why more than 1,500 members use 1stOncology™ to excel in:
Early/Late Stage Pipeline Development - Target Scouting - Clinical Biomarkers - Indication Selection & Expansion - BD&L Contacts - Conference Reports - Combinatorial Drug Settings - Companion Diagnostics - Drug Repositioning - First-in-class Analysis - Competitive Analysis - Deals & Licensing
Schedule Your 30 min Free Demo!
The poster presentation highlighted the potential implementation of its liquid biopsy platform using multimodal deep learning technology to detect colorectal cancer in clinical data. The study incorporates 1,506 colonoscopy-verified normal samples, 130 AA patients, and 302 CRC patients (with a breakdown of stages). This innovative approach demonstrated high sensitivity for CRC detection across all stages, including early-stage lesions, while maintaining high specificity.
"The development of non-invasive screening methods for colorectal cancer is crucial for improving early detection and patient outcomes," said Eun-Hae Cho M.D., Ph.D., Chief Scientific Officer at GC Genome. "By emphasizing the necessity for a non-invasive approach, this research brings us nearer to the development of a convenient, accessible screening option for patients. It has the potential to bridge the current screening gap and surpass the limitations of traditional methods. And we are excited to continue our work to bring this technology to patients as soon as possible."
Key Findings of the Study:
The multimodal deep learning algorithm achieved high sensitivity for CRC detection, ranging from 80.2% to 84.0% across all stages.
The algorithm also demonstrated promising accuracy in detecting AA lesions, with a sensitivity of 63.0%.
The use of colonoscopy-verified normal samples strengthens the study’s foundation and paves the way for future clinical translation.