Improving cancer care and outcomes is dependent on many factors, but having good quality data on which to select treatment pathways, build predictive models and assess population patterns is essential.

However, much of the detailed and rich insights are trapped in narrative style surgical and clinical notes, pathology and radiology reports. This is the data needed to support treatment selection, predictive models, better understand cancer and lead towards a learning healthcare system, commonly viewed as essential for improved efficiency and patient outcomes.

NLP has been growing rapidly in healthcare, initially in research, but now in widespread use for computer aided coding and computer aided document improvement. NLP is set to grow significantly in coming years to address the needs expressed above and to support improved cancer care.

By applying NLP, significant impact can be achieved in improving cancer care by targeting the following areas:

  1. Identifying potential clinical trials matches
  2. Advanced information extraction from complex patient documents
  3. Precise information retrieval for clinical case histories and outcomes studies
  4. Streamlining cancer registry processes
  5. Application of predictive models and care coordination rules to unstructured patient narratives
  6. Semantic enrichment of patient documentation to improve searching
  7. Analyzing patient narratives for insights into treatment outcomes
  8. Assessing the impact of genetic aberrations on disease
  9. Supporting tumor boards

To download the whitepaper, you will first have to fill out a webform:



9 ways to improve cancer insights with NLP