Virtual Library

Start Your Search

Xiaowen Cao



Author of

  • +

    P2.01 - Advanced NSCLC (Not CME Accredited Session) (ID 950)

    • Event: WCLC 2018
    • Type: Poster Viewing in the Exhibit Hall
    • Track:
    • Presentations: 1
    • Moderators:
    • Coordinates: 9/25/2018, 16:45 - 18:00, Exhibit Hall
    • +

      P2.01-35 - Predicting Risk of Chemotherapy-Induced Severe Neutropenia in Patients with Advanced Lung Cancer (ID 13500)

      16:45 - 18:00  |  Author(s): Xiaowen Cao

      • Abstract
      • Slides

      Background

      Neutropenia is associated with the risk of life-threatening infections, chemotherapy dose reductions and delays that may compromise treatment outcomes. The goal of this study was to develop simple prediction model for severe neutropenia in lung cancer.

      a9ded1e5ce5d75814730bb4caaf49419 Method

      A lung cancer dataset was assembled using data from existing national cooperative group phase II/III trials conducted between 1991-2010. Chemotherapy trials in patients with stages III and IV non-small cell lung cancer (NSCLC) or extensive small-cell lung cancer (SCLC) were included. We randomly selected 2/3 patients to derive the model, and the remaining were used for validation. Models were built with stepwise logistic regression and lasso regression on imputed data sets. We fitted the model on the imputed training data sets individually to get 10 models with 10 sets of selected predictors. Next we picked the union set and the intersection set of predictors from the models. The variables in the final model were selected by lasso regression, and then fitted into a logistic model. The performance of the model was evaluated by receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC).

      4c3880bb027f159e801041b1021e88e8 Result

      The dataset was randomly separated into training [n=7606 (67%)] and testing sets [n=3746 (33%)]. The final predictive model included: Age (>65 years), gender (male), weight (kg), BMI, insurance status (yes/unknown), stage (IIIB/IV/ESSCLC), number of metastatic sites (1, 2 or ≥3), individual chemotherapy agents (gemcitabine, taxanes), number of chemotherapy agents (2 or ≥3), planned use of growth factors, associated radiation therapy, previous therapy (chemotherapy, radiation, surgery), duration of planned treatment, pleural effusion (yes/unknown), performance status (1, ≥2) and presence of symptoms (yes/unknown).

      wclc figure.jpg

      Figure: ROC Curve for Final model AUC=0.8306

      8eea62084ca7e541d918e823422bd82e Conclusion

      We have developed a relatively simple model with variables that are routinely available prior to treatment, to predict for neutropenia. This model should be validated prospectively.

      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.