false
Catalog
2023 World Conference on Lung Cancer (Posters)
P1.13. Deep Multi-omic Blood-Based Biomarker Disco ...
P1.13. Deep Multi-omic Blood-Based Biomarker Discovery in People with Smoking History Demonstrates High Early Detection of Nsclc - PDF(Slides)
Back to course
Pdf Summary
Researchers at PrognomiQ, a biotech company in California, have developed a blood-based multi-omics approach for the early detection of non-small cell lung cancer (NSCLC) in current and former smokers. The study included a total of 1,031 subjects, with 361 NSCLC cases, 340 non-cancer controls with pulmonary and/or gastrointestinal co-morbidities, and 330 healthy controls. A machine learning classifier was trained using a subset of 441 current or former smokers, including 153 NSCLC cases and 288 controls. The classifier was developed using transcriptomics, proteomics, and metabolomics data obtained from blood samples. The multi-omics approach showed high sensitivity and specificity in detecting NSCLC, with an AUC of 0.93 in the validation set. The classifier had a sensitivity of 82% and a specificity of 84% across all stages of NSCLC. Specifically, the sensitivity for stage I and stage II-IV NSCLC was 80% and 83%, respectively. <br /><br />The study demonstrated that the multi-omics approach, including profiling mRNA, proteins, and metabolites in blood samples, has the potential to provide a powerful tool for developing liquid biopsies with high sensitivity and specificity for early detection of lung cancer. This approach could help overcome challenges in using liquid biopsies routinely in clinical practice. It offers promise for early detection, identification of genetic mutations targeted by personalized therapies, monitoring disease progression and treatment response, and detection of cancer recurrence. The findings provide a foundation for the development of a multi-omics assay for peripheral blood-based liquid biopsies in lung cancer.
Asset Subtitle
Brian Koh
Meta Tag
Speaker
Brian Koh
Topic
Screening & Early Detection: Biomarkers/Imaging Technology
Keywords
PrognomiQ
biotech company
blood-based approach
NSCLC
early detection
smokers
machine learning classifier
liquid biopsies
genetic mutations
multi-omics assay
×
Please select your language
1
English