Blog
Domain Expertise and NLP Data Factory are a Winning Combination in the Crowded AI Field
Jane Reed, Director, Life Sciences
Jul 14, 2021

The exciting dichotomy of artificial intelligence, or AI, in healthcare and life sciences is that it is exploding, and yet, most companies have really only scratched the surface of its potential. While many organizations have used natural language processing (NLP) “point solutions” to extract insights from textual data, the value of NLP is truly transformational when you meld the technology with rigorous scientific expertise — an intersection at which IQVIA sits squarely.

When used in healthcare, NLP algorithms can search the 80 percent of medical content in documents and databases that is unstructured, including clinicians’ notes, social media, scientific literature, pathology reports and other internal or external organizational documents. NLP unlocks the ability to stream data from these diverse unstructured sources into a technology platform that surfaces text-based insights to support better decisions from bench to bedside.

It is impressive technology on its own, but without embedded domain expertise, many NLP solutions struggle to properly analyze the healthcare industry’s notoriously complex and varied language. IQVIA’s solutions, like the NLP Data Factory, solve this challenge by combining industry-leading NLP with deep domain knowledge, allowing life sciences companies to transform processes and surface value from textual data in ways that are truly game changing. From validating assumptions to expediting development processes and optimizing commercialization, when this combination of NLP is deployed at scale, its possibilities skyrocket. Here I’ll explain a few ways we are solving life sciences’ common challenges.

Capturing the voice of the customer on topics and trends
We recently worked with a client who wanted track trends based on product-related questions across 50 different categories. These categories ranged from simple questions, like adverse events or demographic information, to more complex topics like contraindication, whether patients are switching medications, off-label use, or an uptick in dose-related questions. They also wanted to identify novel requests and topics coming out of customer verbatims.

IQVIA’S comprehensive understanding and experience with the kinds of inputs the customer needed to assess allowed us to offer a custom solution that could rapidly deliver the right insights. To capture the voice of the customer on standard categories and novel topics concurrently, we used a hybrid approach that paired NLP with machine learning. First, we set up an NLP Data Factory automated workflow to tag and enrich the incoming verbatims with those categories that were already well known. Then we took that same information and used it to identify the right attributes for machine learning classifiers like drug, disease, and dosage and built an algorithm to cluster the verbatims based on similarity. The customer now uses the resulting system across 20 different product brands and diverse therapeutic areas to better understand what topics people are talking about, how they are changing over time, and signals on novel topics.

Meeting pharma’s high-demand safety case processing needs
On the journey from drug discovery through development to post-market surveillance and patient care, the amount of textual information is astronomical, and patients and regulators expect zero gaps in safety intelligence. The NLP Data Factory was built to tackle these kinds of broad, high throughput areas with phenomenal speed and accuracy.

In another customer example, a top 20 pharma company used IQVIA NLP to auto-code adverse events to the standard MedDRA term, reducing their manual coding time by 50 percent. At the onset of the project, the client was finding that 70 percent of their incoming adverse events required labor-intensive manual MedDRA coding. With the NLP approach, the customer has been able to double their auto-coding capacity, while reducing manual coding time by 50% and improving coding consistency compared to manual review.

The NLP Data Factory allows healthcare and life science organizations to apply award-winning NLP to huge volumes of data across their enterprise. It easily scales with their needs, integrates with diverse sources of unstructured data, is built with deep domain expertise embedded, and allows customers to start extracting value from text on day one. As more and more organizations are looking to use NLP in their enterprise data transformation, IQVIA’s sweet spot marrying decades of domain expertise with Linguamatics’ industry-leading NLP has us well positioned to lead the pack in NLP solutions for life sciences for years to come.

Contact Us