Novo Nordisk Uses Natural Language Processing to Drive Innovation
Early Scientific Intelligence pipeline gives 360 degree view of “novelty” in diabetes and obesity
We hear a lot these days about evidence-based decision making. Particularly in the current climate, it’s critical that governments, businesses, health organisations and individuals are guided by facts and evidence, not fiction and hearsay. But what do we really mean by evidence-based decision making? Ideally, before making any decision, you want to be able to gather all relevant information, synthesized from different relevant sources. This approach allows you to see the overall picture, drill down to details, understand and weigh up the evidence and therefore make the best decision possible.
Creating a hub of evidence
Getting a comprehensive view of the whole picture is something Linguamatics pharma and healthcare customers need for their decision making in many different arenas – and that often means being able to integrate information from unstructured textual data streams together with data from structured sources. Capturing and integrating the information from a range of document sources can build a landscape of knowledge, a “hub” of evidence. Evidence hubs can be developed for discovery, development, regulatory affairs, safety, patient risk; with input data sources and output dashboards or alerts tailored as needed.
Novo Nordisk are using this integrated approach for an “Early Scientific Intelligence” evidence hub. Sten Christensen & Brian Schurmann (Novo Nordisk) presented on this innovative project at our virtual NLP summit on Thursday 4th June 2020.
External collaboration and partnerships are key to early innovation. All pharma need to feed their development pipeline with the most up-to-date information that’s relevant to their scientists, researchers, out-sourcing and in-licencing teams. This could be the latest information about novel drugs, targets and pathways, biotech companies of interest, university technology offerings, clinical trials in relevant therapeutic areas.
Novo Nordisk want to increase the number of pipeline projects based on external collaborations. To capture the 360 degree view of potential opportunities, as early as possible, they need to enable all their scientists to act as scouts, and have access to the essential snippets of information for that lightbulb moment when all the connections come together.
NLP extracts key information to deliver evidence for innovation
The Novo Nordisk team have developed a semi-automated workflow incorporating Linguamatics NLP to extract key information from a broad range of data sources (both internal and external). These include scientific abstracts, patents, grants, news, tech transfer offices from universities around the world, and more. NLP queries run across sources, for the key therapeutic areas of interest to the Novo Nordisk R&D community. The resulting output are curated and provided via InfoDesk (https://www.infodesk.com/) which provides easy-to-consume alerts to the broader Novo Nordisk researchers. The combination of Linguamatics NLP and InfoDesk newsletters means that the pipeline delivers data that the end users can interact with, drill down to, investigate and assess, so the data have a long afterlife.
This Early Scientific Intelligence pipeline provides an early bird’s view of potential opportunities for in-licensing or external collaborations, for example. Novo Nordisk are integrating technologies and data to improve their R&D pipeline. Their solution enables all their scientists to access all the evidence needed – the “whole picture” – for their innovation.
Figure 1: Snippets of information captured using NLP for that lightbulb moment. An integrated approach enables connections to be created across different data sources. The ESI pipeline newsletters provide regular updates and push updates on mobile for the most important news. Scientists can add comments to the feeds, imparting “the wisdom of the crowds” to the evidence hub. Interactive dashboards with up-to-date landscapes for each therapy area allow the scientists to explore all known data, get the big picture, and enable data driven decision making.
For more information
GET IN TOUCH