This is Part 2 of a three-part series exploring the value NLP delivers across the enterprise. Part 1 takes a deeper look at the transformative power of NLP across specific functions. Part 3 will explore applications of NLP through the lifecycle of a molecule.
“Putting NLP to Work: How augmented intelligence helps experts be more effective and efficient in their day to day”
Gone are the days when natural language processing, or NLP, was reserved for data geeks and career analysts. Today’s NLP is democratized so that even business users with little to no technology expertise can apply it to their day-to-day work. The capability to simplify access and to move analytics to the user community is advancing on an almost daily basis – and no matter what role you hold across the drug development spectrum, this is great news. We often talk about how NLP supports an organization in its big-picture goals, but today, let’s explore some specific ways NLP is positively transforming the work experience for employees.
Identifying the biological origin of a disease and potential targets for intervention demands a systematic review of the public domain literature. But with ever-changing intelligence, trying to keep abreast of all the relevant literature you need to identify targets and understand the association of genes and diseases becomes an almost impossible task. There is an unintended bias, since the expertise of key team members guides the initial search.
With NLP solutions, project teams can rapidly access and analyze key information relevant to discovery. Users can search flexibly across a variety of data types (like enzyme activity or expression levels of particular genes) and to find relationships between known or novel markers, and diseases, mutations, drugs and more. At the end of the day, NLP-powered project teams working on discovery enjoy a massive reduction in manual curation, a more comprehensive search of the content, and accelerating timelines though faster, simplified insights.
In order to ensure the safety of drugs on the market, rigorous testing is carried out throughout the pipeline, and mountains of critical data are both generated and sought from unstructured text – from internal safety reports, scientific literature, individual case safety reports, clinical investigator brochures, patient forum, social media, and conference abstracts. Safety teams are charged with intelligent search across these hundreds of thousands of pages to support decision-making.
With today’s NLP, safety teams can use NLP text mining to streamline the literature review process for pharmacovigilance. They can also use NLP search tools to review medical literature for safety signals and enhance the searchability of internal preclinical toxicology safety reports. What used to take months can now be completed in just days by NLP-powered safety teams – with richer, more precise results than manual review can achieve.
With nearly 200,000 study records in clinicaltrials.gov, testing over 70,000 unique pharmacotherapies in approximately 190 countries, clinical development teams tasked with trial analytics, design research, meta-analysis and competitive intelligence reporting have a tall order. Many project teams are overloaded and reaching burnout with the mountain of manual review they must climb.
With NLP, these teams can easily run queries over the detailed unstructured textual record fields in databases such as ClinicalTrials.gov, Cortellis Clinical Trials Intelligence, WHO ICTRP, or Citeline's TrialTrove to rapidly identify, extract, synthesize and analyze relevant information such as clinical trial site, selection criteria, study characteristics, patient numbers and characteristics that would not be possible using other approaches. With this data unlocked, they can rapidly answer questions like, “What are appropriate clinical endpoints for this condition?” “Which investigators are experts in running trials for this specific disease?” and “Who else has drugs in trials for my indication of interest?”
Performing regulatory compliance gap analysis is often long and tedious. In one of our client meetings, the customer asked us for an honest assessment of what it would take to manage the ingestion and extraction of 40,000 regulatory documents related to the acquisition of new small molecule asset for submission housed across multiple SharePoint environments. The regulatory team was up against a wall – the risk of missing the submission deadline was high, but so too was the cost of manual review.
Applying NLP, we were able to rapidly map and visualize the relevant content. As a result, the regulatory team could investigate and mine the content through multiple means well within their deadline.
In a pre-NLP world, brand researchers were required to go through highly tedious and complex methods of acquiring qualitative data and commercial intelligence around products. They manually read through all available textual information, labeled responses, and grouped them into categories in a process that was long and often missed important insights.
Now, using NLP commercial teams can capture streams of internal and external intelligence around product brands into one integrated environment, for visual analytics to aid brand team decisions. They can also look across scientific literature and prescription databases to enable a better understanding of drug-drug interactions and co-prescription trends quickly and easily.
There’s no question that from discovery to commercial efforts, NLP is a game-changing technology for helping a variety of roles rapidly unlock the value of words from documents, including scientific literature, clinical research reports, text-based information within databases and news or social feeds. At the working level, that translates to greater efficiency and simpler completion of those dreaded tasks that involve manual review and large amounts of data. While we often emphasize the value NLP brings to the enterprise in terms of efficiency and data richness, we’d be remiss to underestimate its ability to improve the day-to-day experience of every organization’s greatest asset: its employees.
For more information on what the latest NLP solutions can do for you and your employees, check out our recent webinar, Step Change: Unlocking the Hidden Value of Your Enterprise’s Dark Data. Be on the lookout for Part 3 of this series, which will explore applications of NLP through the lifecycle of a molecule, and don’t miss Part 1, which shares how NLP visualizations can transform your enterprise.