Spring is a lovely time to be in Cambridge – winter is finally moving on, the spring bulbs are out and the trees are in blossom. Time for Linguamatics Spring Text Mining Conference, which again this year was blessed with lovely sunshine. And of course, the opportunity to hear the latest about Linguamatics products and some new and fascinating use cases from our customers.

In March 2019, attendees from across pharma and healthcare came to our Spring Text Mining Conference, for hands-on workshops, a Healthcare Hackathon, networking and great presentations. The presentations covered innovations in using Natural Language Processing (NLP) to get more value from a range of unstructured text, covering electronic medical records, regulatory documents and patient social media verbatims.


Digital transformation often induces a disruption in our systems, in the way we use technology, human intelligence and processes to enhance business performance. Life science organizations are generally embracing the necessary digital revolution but digital transformation demands data transformation, which includes developing strategies to access information buried in text.

Data-driven decision making

During the upcoming Bio-IT World Conference & Expo, Jane Reed, Linguamatics Head of Life Science Strategy, will present a talk on "Natural Language Processing: enabling data-driven rather than document-driven decision making". Natural Language processing (NLP) allows organizations to focus on data-driven rather than document-driven decision making in a timely manner. The technology is already helping people in life sciences and healthcare, even non-programmers, to transform unstructured text into actionable structured data that can be rapidly visualized and analyzed, for decision support from bench to bedside.


Recently, I found myself in a discussion with some colleagues around whether artificial intelligence (AI) could increase commercial engagement and sales productivity; specifically, the Linguamatics flavour of AI, Natural Language Processing (NLP). My first reaction was no – our customers tend to use NLP to pull out critical information for safety assessment from internal reports, genotype-phenotype associations from literature, inclusion/exclusion criteria from clinical trial records; and many more examples that impact drug R&D.

But as the discussion progressed, I realized that as our customers drill more and more into the power of NLP to unlock value from real world data, the answer is actually yes. NLP enables data-driven, rather than document-driven decision support, by extracting key concepts and context from unstructured documents, which can then be rapidly reviewed and analysed. So, since much real world data is unstructured text, NLP can bring real productivity gains.

Challenges for pharma medical field teams

Let me give you some background, and then some examples.

Over recent years, pharma sales reps and medical science liaison staff (MSLs) have faced increasing challenges around access to Key Opinion Leaders (KOLs), physicians and prescribers, due to a more restrictive regulatory environment, new healthcare business models and evolving economic conditions. The boundaries for how pharma sales reps can interact with physicians are more limited, for example the “lunch and learn” meetings that used to be a key tool have been significantly curtailed. In parallel, the pressures on physicians to see more patients also reduces the time they have to learn about new drugs or improved therapies.


Real world evidence provides significant insight into how a drug or drug class performs or is used in real world medical settings. Real world evidence (RWE) and real world data (RWD) can inform all phases of pharmaceutical drug development, commercialization, and drug use in healthcare settings.

The ability to quickly transform real world data sources (e.g. EHRs, or patient-reported outcome data from forums, social media) into evidence can improve health outcomes for patients by helping pharmaceutical companies be more efficient in drug development and smarter in commercialization.

Voice of the customer call feeds: a valuable source of real world data 

One source of patient reported outcomes available to pharma companies are the feeds that come into the 1-800 call centers – calls from patients, carers, healthcare professionals or pharmacists, asking questions covering many different issues, such as:


Learning more about drugs understanding in the market

How can pharma product managers efficiently learn how their drugs are faring with patients in the market?

Product managers and teams in pharmaceutical companies need to know what patients and healthcare professionals are reporting and asking about their drugs as they are used in the market, in order to discern trends and patterns and respond appropriately. Real world data (RWD) on drug usage and patient behaviours is available in multiple formats from myriad sources, but mining these disparate structured and unstructured sources with traditional manual search and curation is time-consuming and inefficient.

Novo Nordisk wanted to accelerate, automate and scale this process to provide enhanced access to the extracted information for superior and actionable insights.

Natural Language Processing-based Text Mining at Novo Nordisk

Novo Nordisk was already using the Linguamatics NLP platform in-house on multiple individual text mining projects with good success (e.g. reducing a publication gap analysis from three-to-four people for six weeks to a few hours). They wanted to capitalise on this success for real world data about their diabetes therapeutic products, from medical affairs team, healthcare professionals, and patients.