Author of

• 18120

  +

  OA19 - Translational Research in Early Stage NSCLC (ID 402)

  • Event: WCLC 2016
  • Type: Oral Session
  • Track: Early Stage NSCLC
  • Presentations: 1
  • Moderators:G. Heller, G. Goss
  • Coordinates: 12/07/2016, 11:00 - 12:30, Schubert 3

  • 18123

    +

    OA19.03 - Identify Lung Adenocarcinoma in Situ among Pulmonary Micro-Nodules through Blood Gene Expression Profiles (ID 4749)

    11:20 - 11:30  |  Author(s): C. Cheng
    • Abstract
    • Presentation
    • Slides

    Background:
    The national lung cancer screening test (NLST) confirmed: low dose CT screening could reduce lung cancer mortality. However, the high false-positive rates of LDCT screening, especially the difficulty of diagnosis of micro-nodules with size less than 10 mm highlight the need of complementary biomarkers to discriminate micro-nodular lung cancer from benign pulmonary diseases.
    
    Methods:
    The blood gene expression profiles of 46 lung cancer patients, 38 pulmonary lesions and 51 healthy were investigated to identify the lung cancer-specific genetic signatures. The lung cancer patients containing micro-nodules less than 10 mm were surgically and pathologically diagnosed as lung adenocarcinoma in situ
    
    Results:
    A self-training logistic regression method was used to identify the lung cancer-specific gene signatures as we previously reported. Six genes, including DDX51, PSME2, ACTL6A, GMEB1, FAM200B, GEMIN6, were identified for discriminating lung adenocarcinoma in situ from health and benign pulmonary diseases. The performance of the six-gene panel for diagnosis of lung adenocarcinoma in situ identified was exhibited in Table 1. Through self-training SVM classifier, the logarithmic odds of each sample was calculated and exhibited, in which the cutoff value was set as zero in logarithmic odds for differentiating lung cancer from benign and control group. The predictive model based on 6-gene panel correctly classified 43 of 46 lung cancer, 39 of 42 benign pulmonary diseases with 93% accuracy, 94% sensitivity, and 93% specificity and 0.97 of ROC AUC.
    
    Conclusion:
    The predictive model based on 6-gene panel (DDX51, PSME2, ACTL6A, GMEB1, FAM200B, GEMIN6) can be used for discriminating between the malignant or benign nodules with size less than 10 mm
    
    

    Only Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login, select "Add to Cart" and proceed to checkout. If you would like to become a member of IASLC, please click here.

    Only Active Members that have purchased this event or have registered via an access code will be able to view this content. To view this presentation, please login or select "Add to Cart" and proceed to checkout.