Extracting Real-World Evidence from Large-Scale Population Health Documents

June 1 2017

Pentavere Research Group of Toronto, Canada, was developing a platform to provide health insights from Real-World Evidence (RWE). Pentavere’s aim is to improve healthcare efficiency by allowing life science companies and healthcare providers to understand the impact of clinical decisions made in the primary care setting.

The company’s proprietary platform, daRWEn™, uses digitized, de-identified, and aggregated health information, but much of the valuable data that it wanted to include was locked inside free-form text, making it difficult to extract. Pentavere soon realized that it needed to incorporate natural language processing (NLP) capabilities into its platform in order to access these RWE insights. To achieve this in a timely and efficient manner, it chose to integrate the Linguamatics I2E NLP solution into daRWEn™.

Why Linguamatics? There were several important factors, including:

  • NLP that just works—Pentavere needed to make unstructured data more usable, and Linguamatics had already implemented capabilities that matched Pentavere’s requirements. That Linguamatics was also strong in healthcare and life science was an added bonus.
  • Linguamatics’ excellent customer service is responsive and provides world-class support.
  • Scalability—integrating I2E’s powerful NLP capabilities into the daRWEn™ platform provides RWE based on a far greater sample size than that available from other sources.
  • With I2E, open-ended searches reveal insights that users never knew they needed! But if exact data is sought, precise queries can pull specific concepts with reliability and accuracy.

A user-friendly platform means that users can be up and running quickly, and queries can often be reused across therapeutic areas.

“We quickly realized with other vendors that their products didn’t really live up to what they were promising. With Linguamatics, they said ‘we can do this and this’ and then backed up their promises by delivering a proof of concept up-front.” 

Steve Aviv, Chief Information Officer, Pentavere Research Group

Integrating I2E into the daRWEn™ platform meant that Pentavere could get to market more quickly, while keeping its development costs down. The full Linguamatics solution was delivered by just one full-time equivalent (FTE) developer in 12 months, compared to estimates of five FTEs and a delivery time of 24 months using open source systems.

Download the Case Study