Skip to main content

Overcoming Challenges in Rare Disease Research: Uncovering Hard to Find Patients using NLP in Electronic Medical Records


Time: 8:00am PST, 11:00am EST, 4:00pm GMT, 5:00pm CET

Duration: 60 minutes


In pharma and healthcare, understanding the real world impact of therapies on patients is critical. Real world insights (RWI) can inform all phases of drug development, commercialization, and drug utilization in healthcare settings.  These insights can shed light on real world clinical effectiveness or safety profiles of products across a broad patient community as well as difficult to identify rare disease patient populations. Access to high quality robust real world data (RWD) is key to generate RWI accelerating progress of research. In this webinar, we will present on use of IQVIA NLP to enhance the AEMR data by standardizing the different ways rare diseases are mentioned, covering 60+ rare diseases including ALS, hereditary angioedema, fragile X, familial hypercholesterolemia. 

Electronic medical record data is one of the most commonly used real world data sources along with claims, hospital data, and other RWD. IQVIA provides one of the largest linkable, commercially-available EMR databases in the industry. IQVIA Ambulatory EMR-US (AEMR-US) provides an in-depth look into the interactions between patients and their healthcare providers. Most important, AEMR data provides clinically rich metrics that are not available in other RWD sources.  
As with many RWD sets, there are many data fields that contain unstructured text, which are therefore hard to use in downstream analyses. IQVIA NLP-based text analytics is used across the industry to transform unstructured source data into clinical and research decision support insights. In this webinar, we will review how NLP was used to identify four rare diseases and clinically rich profiles were generated using IQVIA AEMR. 

What will you learn?

  • Value of IQVIA Ambulatory EMR-US to identify hard-to-find populations with rare diseases.
  • How natural language processing (NLP) text mining can extract relevant structured data from unstructured text including provider notes using ontologies, flexible queries, and linguistic processing.
  • Real-life success stories from pharmaceutical companies such as Novo Nordisk, Bristol-Myers Squibb, Iowa University, and others who are using NLP to access and gain valuable insights from a variety of data sources including call-center feeds, patient forums, field medical affairs notes, and electronic medical records.


Jane Reed - Director, Life Science
Jane Reed
Director, Life Science
Kimberley Jordan
Kimberley Jordan
Director, US Real World Data and Technology at IQVIA

Ready to get started?

Request a Demo

Questions? Ask our experts