Author of

• 31680

  +

  P2.16 - Treatment in the Real World - Support, Survivorship, Systems Research (ID 187)

  • Event: WCLC 2019
  • Type: Poster Viewing in the Exhibit Hall
  • Track: Treatment in the Real World - Support, Survivorship, Systems Research
  • Presentations: 1
  • Moderators:
  • Coordinates: 9/09/2019, 10:15 - 18:15, Exhibit Hall

  • 31702

    +

    P2.16-20 - Big Data and Survival Predictors in Lung Cancer Patients (ID 1943)

    10:15 - 18:15  |  Author(s): Juan Manuel Tuñas
    • Abstract
    • Slides

    Background
    

    Lung cancer is the most common and fatal one (18% of all cancer deaths). Parameters which imply better survival are still unknown.

    The objective of this project is to turn the large amount of data from each patient into exploitable information.

    Method
    

    Between 2008-2019, 935 non-small cell lung cancer patients from our hospital were enrolled in an observational study.

    Unstructured data was obtained from the patient Electronic Health Records.

    Politecnica University from Madrid made the information analysis using Big Data and machine learning techniques.

    Result
    

    A total of 251.730 documents have been analyzed from 935 patients, 54% in stage IV.

    EGFR/ALK mutation was found in 9%, showing better OS than non-mutated (23.5 months vs 12 months, log-rank p=0.016). Survival curves are shown in figure 1.

    In a multivariate analysis (table 1), independent predictors of mortality were male sex, squamous histology and PS status. Additionally, independent predictors of survival were receiving immunotherapy, surgery treatment or developing endocrine toxicities.

    Conclusion
    

    Big data is a very useful tool to exploit a large amount of lung cancer data, increasing knowledge about these disease and allowing the development of survival predictive models.

    
    This work was supported by the EU H2020 programme, under grant agreement Nº 727658 (Project iASiS).

    

    

    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.