Virtual Library

Start Your Search

Nancy Diao



Author of

  • +

    MA18 - Modelling, Decision-Making and Population-Based Outcomes (ID 920)

    • Event: WCLC 2018
    • Type: Mini Oral Abstract Session
    • Track: Treatment in the Real World - Support, Survivorship, Systems Research
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/25/2018, 13:30 - 15:00, Room 201 F
    • +

      MA18.01 - Non-Small Cell Lung Cancer Risk Assessment with Artificial Neural Networks (ID 13532)

      13:30 - 13:35  |  Author(s): Nancy Diao

      • Abstract
      • Presentation
      • Slides

      Background

      Lung cancer is a heterogeneous disease with many clinically important subtypes. Given the complexity of classification, there is room for innovative risk assessment tools to help ascertain prognosis and management. In this work we tested an Artificial Neural Network (ANN) to stratify patients into clinically significant low and high risk categories.

      a9ded1e5ce5d75814730bb4caaf49419 Method

      CT imaging, survival, and cancer staging data was extracted for a sample of 311 patients with Stage-I (n = 186) and Stage-II (n = 125) non-small cell lung cancer (NSCLC) from the comprehensive Boston Lung Cancer Survival (BLCS) cohort. Median follow-up from time of diagnosis was 3.5 years, with 86% 2-year survival. A deep convolutional neural network pretrained on ImageNet was used, with fine-tuning of the last convolutional layers, dense layers, and softmax for stratification. Inputs of this model were 50 x 50 mm2 image patches. Training was performed on 182 labeled CT scans (112 Stage-I and 70 Stage-II). 46 cases were used for initial cross-validation, with an independent test set of 83 cases. The median prediction probability from the ANN was used as a cutoff to divide patients into low and high risk groups.

      4c3880bb027f159e801041b1021e88e8 Result

      The model was able to perform classification of cancer stage on the heterogeneous test set (AUC = 0.73, p< 0.0005). The test set was split evenly into low risk (n = 42) and high risk (n= 41) groups based on model predictions. There was statistically significant separation in the Kaplan Meier-estimates for survivorship in the two stratified groups (p < 0.02).

      ialsc_figure.png

      8eea62084ca7e541d918e823422bd82e Conclusion

      ANNs can be effective tools for quantitative risk stratification in NSCLC. In addition to the potential for real-time clinical decision support, ANNs may also help create new paradigms in lung cancer risk assessment. The models have the capacity to perform suprahuman computations, which can help meet future demands of clinical practice, given expanding digital-imaging volumes.

      6f8b794f3246b0c1e1780bb4d4d5dc53

      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.

  • +

    P1.11 - Screening and Early Detection (Not CME Accredited Session) (ID 943)

    • Event: WCLC 2018
    • Type: Poster Viewing in the Exhibit Hall
    • Track:
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/24/2018, 16:45 - 18:00, Exhibit Hall
    • +

      P1.11-05 - Metabolomic Profiling for Second Primary Lung Cancer Among Lung Cancer Survivors (ID 13995)

      16:45 - 18:00  |  Author(s): Nancy Diao

      • Abstract

      Background

      Survivors of lung cancer(LC) have a high risk of developing second primary lung cancer(SPLC), the incidence of which is 4-6 times higher than that of initial primary lung cancer(IPLC). While national lung screening guidelines have been established for IPLC, no consensus guidelines exist for LC survivors. Furthermore, the factors that contribute to SPLC risk have not yet been established. The purpose of this study is to examine the potential of metabolomics to identify non-invasive blood-based biomarkers for SPLC screening.

      a9ded1e5ce5d75814730bb4caaf49419 Method

      We applied an untargeted metabolomics approach based on a liquid chromatography-tandem mass spectroscopy(UPLC-MS/MS) method to discover metabolic biomarkers using blood serum samples from the Boston Lung Cancer Study. Our study cohort consisted of 177 subjects diagnosed with IPLC between 1992 and 2012 and who survived >=5 years after the initial diagnosis. The cohort included 82 SPLC cases and 95 matched controls (i.e. IPLC patients without SPLC as of Dec, 2017) based on the age of initial diagnosis, sex, race, and smoking status. We applied random forest and Welch’s t-test to identify metabolomic features associated with SPLC risk and to build a risk prediction model.

      4c3880bb027f159e801041b1021e88e8 Result

      Our analysis detected 1008 named and 316 unnamed metabolites. The metabolites that were statistically significantly associated with SPLC risk (False Discovery Rate q-value<0.05) included 5-methylthioadenosine (MTA), phenylacetylglutamine, and umbelliferone sulfate, which showed 1.4-3.8 fold increases among SPLC cases versus controls (Figure 1). These metabolites were involved in amino acid, peptide, and xenobiotics pathways. The stratification by quintiles of estimated risk using the prediction model based on the metabolites showed that the observed incidence of SPLC was significantly higher in the fifth quintile(69.4%) versus the first-quintile(36.1%;P<0.05).

      figure1_splc.jpg

      8eea62084ca7e541d918e823422bd82e Conclusion

      We identified potential metabolic biomarkers for SPLC among LC survivors. A risk-stratification approach based on metabolic biomarkers can be potentially useful for identifying high-risk LC survivors to be screened by CT.

      6f8b794f3246b0c1e1780bb4d4d5dc53

  • +

    P3.16 - Treatment of Early Stage/Localized Disease (Not CME Accredited Session) (ID 982)

    • Event: WCLC 2018
    • Type: Poster Viewing in the Exhibit Hall
    • Track:
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/26/2018, 12:00 - 13:30, Exhibit Hall
    • +

      P3.16-01 - A Multi-Omic Study Reveals BTG2 as a Reliable Prognostic Marker for Early-Stage Non-Small Cell Lung Cancer (ID 13586)

      12:00 - 13:30  |  Author(s): Nancy Diao

      • Abstract
      • Slides

      Background

      Background: B-cell translocation gene 2 (BTG2), which functions as a tumor suppress gene, has been reported to be involved in several cancers. However, no study has focused on its role in lung cancer progression or prognosis. We aimed to investigate the role of BTG2 in early-stage non-small cell lung cancer (NSCLC) survival

      a9ded1e5ce5d75814730bb4caaf49419 Method

      Patients and Methods: This study included 1,230 early-stage (I, II) surgically treated NSCLC patients with methylation and expression data from five international cohorts. We built a prognostic model based on BTG2 methylation. Then, we explored BTG2 expression and NSCLC survival in 3,038 cases, including the above-mentioned cohorts as well as 17 extended public datasets by meta-analysis. Further, we integrated the clinical information, expression, and methylation to build an integration model and evaluated its prediction ability using C-index.

      4c3880bb027f159e801041b1021e88e8 Result

      Results: Three risk CpG probes (cg01798157, cg06373167, cg23371584) were associated with overall survival. The prognostic model based on methylation could distinguish patient survival in the four cohorts [hazard ratio (HR) range, 1.51 to 2.21] and the independent validation set (HR = 1.85). In the expression analysis, BTG2 acted as a tumor-suppress gene in each cohort (HR range, 0.28 to 0.68). A meta-analysis showed high BTG2 expression was associated with better survival (HR = 0.61, 95%CI: 0.54-0.68). The three CpG probes were all negatively correlated with BTG2 expression. Further, the integration model based on BTG2 methylation, expression and clinical information showed a better prediction ability in the training set and validation set.

      8eea62084ca7e541d918e823422bd82e Conclusion

      Conclusions: The methylation and integrated prognostic signatures based on BTG2 are stable and reliable biomarkers for early-stage NSCLC. They may have new applications for appropriate clinical adjuvant trials and personalized treatments in the future.

      6f8b794f3246b0c1e1780bb4d4d5dc53

      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.