APR Sept/Oct 2023 - 76

»
FORMULATION AND DEVELOPMENT
»
interpretation, and generation of natural language by machines. It
enables computers to process, analyze, and derive meaning from
human language in a way that is similar to how humans do, from a
vast range of text types (emails, tweets, literature, reports, reviews
and more).
NLP enables pharmaceutical companies to examine large collections
of documents to discover new information or help answer specific
research questions. The process is useful for identifying facts,
relationships, and assertions that would otherwise remain buried in
huge volumes of textual data. After this information is converted into a
structured form that can be further analyzed, it can be integrated into
databases, data warehouses, or business intelligence dashboards and
used for descriptive, prescriptive, or predictive analytics.
Though the technology has existed for decades, NLP has matured
in recent years, with products such as Siri, Alexa, and Google's voice
search employing NLP to understand and respond to user requests.
More recently, the development of Large Language Models (LLMs,
as made popular by ChatGPT) has invigorated discussions around
application of NLP technologies in fields as diverse as medical
research, risk management, customer care, insurance fraud detection,
and contextual advertising.
Modern NLP solutions are capable of analyzing unlimited amounts
of text-based data without fatigue in a consistent, unbiased manner.
These platforms can understand concepts within complex contexts
and decipher the ambiguities of language to extract key facts and
relationships, as well as provide summaries.
NLP has become an essential technology across pharma drug
discovery, development, and commercialization, in part due to
its ability to outperform traditional methods of search. Although
traditional search engines like Google now offer refinements such as
synonyms and auto-completion, the vast majority of search results
point only to the location of documents, leaving searchers with the
problem of having to spend hours manually extracting the necessary
data by reading through individual documents.
Given the huge quantity of unstructured data that are produced
every day throughout the healthcare industry, from EHRs to social
media posts to medical images, NLP has become a critical tool for
the industry to analyze text-based data efficiently. NLP can help
improve the efficiency, accuracy and innovation of drug discovery
and development processes, by leveraging the vast amount of
unstructured data available in the pharma industry.
In drug discovery,
for example, NLP-powered literature mining
identifies potential drug targets by extracting relevant information
from scientific publications, accelerating target identification
processes. In safety, NLP is used in automated extraction and analysis
of adverse event reports, enabling faster identification of safety
trends and signals for regulatory reporting. And in medical affairs, for
example, NLP can analyze topics and trends from communications
76 |
| September/October 2023
with healthcare professionals, patients, regulators, etc. on medical
information, education, and evidence.
How NLP Helps with Compliance
Leading drug developers are now using NLP for a variety of purposes
within regulatory affairs, including to speed regulatory affairs and
compliance, boost labelling processes, standardize regulatory
data, map to master data management systems, and drive digital
transformation in regulatory processes.
NLP provides substantial value across several regulatory disciplines,
including:
* Regulatory labelling: Access to drug labels from some of the
larger regulatory authorities is important to help labelling teams
find reference information for disease and symptom terms,
contraindications, adverse events, special populations and more.
* Regulatory intelligence: Access to the landscape of regulatory
updates, with integrated data flows to consume textual
documents, both internal (such as corrective and preventive
actions) and external (such as regulatory guidelines and FDA
letter) is essential for regulatory teams.
* Regulatory mapping: Compliance teams need a means of
finding key data attributes from unstructured text documents
and mapping that data to standards, such as Identification of
Medicinal Products (IDMP), a set of international standards that
define the rules that uniquely identify medical products.
Figure 2.
NLP in Action: How Pharma is Using
the Technology
Below are some real-world use cases that highlight how
pharmaceutical companies are using NLP to improve regulatory
compliance and processes:
APR Sept/Oct 2023

Table of Contents for the Digital Edition of APR Sept/Oct 2023
