Natural Language Processing enhances commercial engagement and sales productivity in Pharma

April 1 2019

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.

To be successful, reps and MSLs need to have the right content, impactful and concise, to hand at every opportunity. They need to know who to speak to across their region, and they need to have, at their finger-tips, the current trends, concerns, pain points and perceptions of their drugs, plus information competitor products. So how does NLP fit into this challenging picture? NLP can help provide intelligence on who to call, how to find the right key opinion leaders, trends from real world data and even what is the best collateral to use for a particular healthcare professional (HCP) or drug product. Some snapshots from our customers suggest some innovative practices that can help.

Who to call – finding the right Key Opinion Leaders

One key task where NLP can provide value is the identification of key opinion leaders (KOLs). Many top pharma use NLP to mine scientific abstracts, conference reports, or clinical trial records to extract, structure and visualise who are the KOLs in particular therapeutic areas (read here).

Mining social media can provide insights into newer “digital” key opinion leaders. Novo Nordisk have talked about finding Digital opinion leaders, using Linguamatics NLP to mine Twitter. Novo Nordisk were able to clean the notoriously noisy Twitter data by using NLP algorithms and business rules to identify physicians and medics for key influencers in the obesity area and assess their level of influence by their twitter network.

Understanding real world product issues and trends

Knowing the current thoughts and perceptions of patients, HCPs and KOLs is important; sales reps need to enter every meeting feeling informed, aware and up-to-date. Taking a variety of real world data feeds – (e.g. social media, call centre transcripts, medical field notes and more) and integrating and consolidating these data feeds provide a powerful background in advance of any visit. AstraZeneca, Pfizer, Johnson & Johnson and Novo Nordisk have all presented on using NLP to mine the nuggets from these noisy and varied channels. Workflows use NLP to structure the data and advanced visualisation tools to provide easy-to-digest dashboards, for their medical affairs and product commercial teams to access and assimilate the insights (read here).

NLP can enable sharing of best practices

Identifying the best collateral from MSLs and sales reps for use once a meeting is planned is also an important component for productive conversations. Pharma product teams can use NLP to pull out metadata and map the most commonly used product sheets, slide decks and other product collateral that sales reps use. The metadata enables visualisation of what materials are well used and where MSLs are finding gaps – critical for product teams to know and thus be able to fill.

 topics, trends and resources. This graph shows that Novo Nordisk used NLP to analyse conversations between MSLs and HCPs to extract what materials were used in the conversations.

Fig.1 Novo Nordisk used NLP to analyse conversations between MSLs and HCPs to extract what materials were used in the conversations. Seeing the trends in these clinical insights enable Novo to spot gaps and improve resources. MSL interactions with HCPs may use approved slide decks, package inserts (PIs), factsheets, studies, publications to answer HCP questions, or discuss topics such as safety & efficacy, dosing, cost, special populations, indication, comparisons, competitor products, etc. Using Linguamatics NLP to structure content from the source files, and visualise topics and trends, provided a new tool for generating insights from HCP & ML engagements.

NLP brings insight for pharma product teams

So I had to reconsider my first reaction, and realise that yes, AI – in the shape of NLP – has been proven to bring value to pharma field, medical affairs and sales teams, providing insights and information that can boost communication, understanding and productivity. And, as the volume and variety of real world data source grows, so I am sure that the opportunity for value contributed by AI technologies will grow as well.


Read the original Copyright Clearance Center article here.

Learn more about how NLP can help generate actionable insights from real-world data.