Blog
Extraction and enrichment of textual data at scale has arrived. What can the NLP Data Factory do for you?
Dr. Calum Yacoubian, Director Healthcare NLP Strategy
Apr 16, 2021

Many who have used NLP (natural language processing) in the past would be forgiven for thinking that while NLP tools have proven useful in ad hoc projects, their role within enterprise solutions is unlikely. This is because most NLP projects and developments have been confined to small, specialist teams, tuned specifically for individual needs and problems—until now. Extracting value and meaning from semi- and unstructured data reliably and repeatably is essential, not just in ad hoc use cases, but across the enterprise.

That’s why I’m so excited about the launch of the IQVIA NLP Data Factory, IQVIA’s NLP solution that accurately surfaces and normalizes features of interest at scale to deliver comprehensive value across your organization. Using world-class NLP capabilities, the IQVIA NLP Data Factory embeds seamlessly into existing enterprise architectures and workflows across functions to deliver ready-to-use data and solutions that improve healthcare business outcomes.

The value of textual insights at scale

Enterprise data are incredibly complex. Take medical records, for example. Not only do they combine documentation from across the healthcare ecosystem, but data types from each encounter can also vary widely. To further complicate things, the medical vocabulary is notoriously complicated, with medical terms, concepts, synonyms and acronyms that are dramatically different from standard spoken language. Reviewing and consolidating this data manually is time-consuming and unsustainable; but the analysis is essential to inform appropriate care management, analytics, research, and reporting.

The IQVIA NLP Data Factory was built to address this complexity. It’s powered by the IQVIA NLP platform, which means IQVIA’s unparalleled linguistic processing, machine learning, and domain expertise are built in to deliver accurate terminology matching, pattern extraction, and relationship identification. The powerful blend of machine learning and rules-based processing means that the NLP Data Factory delivers high quality results that can be easily configured and tuned using a simple user interface to deliver highly accurate results across different uses. The multipurpose NLP engine is paired with flexible scaling and deployment options, which mean that textual data can be transformed rapidly at a rate of millions of documents per hour. The output of the NLP Data Factory can be channeled to various locations or uses, from feeding predictive models to surfacing valuable information for visualization in business intelligence tools, such as the IQVIA NLP Insights Hub.

The best of both: leading edge and industry vetted NLP

One of the most promising features of the IQVIA NLP Data Factory is that users get the benefit of a cutting-edge solution that is underpinned by IQVIA’s trusted, tested NLP capabilities. Choosing the wrong NLP solution right out of the gate can deliver lackluster results and potentially make users doubt NLP’s ability to deliver reliable, quality solutions for complex healthcare or life sciences needs. IQVIA’s NLP team has built 20 years of trust across both industries, and our NLP capabilities are world class, award winning, and vetted.

Customers are already seeing huge gains from the IQVIA NLP Data Factory. In one use case, a large insurance company with multiple business lines needed insights from member documentation contained in more than 50,000 documents a day. Once the NLP Data Factory pipeline was implemented, the company improved its processes in days (not months or years), eliminated massive data storage requirements, and today uses the NLP Data Factory to automatically extract more than 500 features of interest across two million documents per hour.

The potential applications of such transformative power are broad. With IQVIA NLP already proving valuable in many domains, enterprise-wide NLP automation can easily be turned to biomarker discovery, safety case processing, risk adjustment, medical affairs insights, clinical trial analytics, and more.

By deploying an NLP Data Factory, healthcare and life sciences organizations can ask broader and more impactful questions of their data to build an ecosystem of knowledge that improves healthcare delivery and drug development.

What can the NLP Data Factory do for you? Check out our solutions page or fact sheet and reach out to us today so we can set up a demo.

Contact Us