How pharma can improve regulatory compliance with AI-based technology
The pharmaceutical industry is among the most heavily regulated in the world – and with increased globalisation and the enhanced understanding of risk, regulation requirements will continue to grow.
For drug developers, regulatory frameworks and reporting requirements are continuously evolving. Keeping up with regulatory changes, including new reporting guidelines and safety requirements, is crucial to avoid compliance issues.
To maintain compliance with constantly shifting regulations, pharmaceutical companies need tools that enable them to discover, highlight, and extract key data within regulatory documents. However, accessing the necessary data can take a significant amount of time, money, and effort, all of which add costs, but not necessarily increased revenue.
To overcome these barriers to data access, many pharma companies’ regulatory teams rely on Natural Language Processing (NLP), an innovative artificial-intelligence-based technology.
A key value of NLP within drug discovery and development is the ability to surface information and insights, without having to manually read each document. NLP text mining uses artificial-intelligence-based technologies to transform the free, or unstructured, text in documents and databases into normalised, structured data suitable for analysis.
Text mining allows drug developers 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 massive quantities of textual data.
How NLP delivers value
Today, NLP is used by leading pharmaceutical companies to speed regulatory affairs and compliance, boost labelling processes, standardise regulatory data, map to master data management systems, and drive digital transformation in regulatory processes.
NLP can deliver significant value in a number of 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.
Use cases for regulatory intelligence and automation
The following are real-world use cases that illustrate how pharmaceutical companies are using NLP to improve regulatory compliance activities.
Data-driven risk management: The biopharma product development and supply group for a top 10 pharmaceutical company needed a better understanding of internal and external risk management data to optimise the formulations, commercial supply, and post-market regulatory compliance of its products.
To help drive those efforts, the company created a data lake to capture relevant information feeds. Internal feeds included deviations, corrective and preventative actions (CAPAs), risks, and response to questions (RTQs). External feeds included FDA warning letters, biological license applications (BLA) review reports, white papers, and industry benchmark repositories.
The company relied on NLP to structure and generate this intelligence data, extracting concepts, relationships, and sentiments embedded in the information. The value of this data is further maximised with easy-to-understand visualisations, enabling end-users to drill down and navigate the information. These data pipelines and workflows are updated automatically, providing the team with a sustainable and scalable reporting of the regulatory landscape, including risks and recommendations to act upon.
Semi-automated regulatory intelligence monitoring: Regulatory teams often rely on manual methods of monitoring regulatory changes, such as having team members perform regular checks of agency websites for recent guidelines, public consultations, and meeting conclusions.
This process is valuable because it provides essential intelligence to identify key concerns, deadlines, events, and regulatory decisions for compounds of interest, but the downside is that it tends to be effort-intensive and time-consuming.
One pharmaceutical company overcame these issues by employing NLP to provide a workflow to semi-automate information acquisition and summaries. A key feature of the company’s approach is to integrate NLP technology with Large Language Models (LLMs) to enhance human teams’ abilities and drive more effective decision-making.
The company used this combined approach to create a regulatory intelligence assistant, which provided team members with easy question-and-answer access to updated regulatory intelligence and risk categorisation for substances of interest. By using this model, the company can deliver dynamic insights into various regulatory landscapes, highlighting major areas of risk, by extracting, summarising, and classifying information for user-specified substances.
To conclude
For drug developers, effective access to information on regulatory guidance, standards, and safety intelligence is essential, but remains challenging and time-intensive because new information emerges constantly. Because manual search is error-prone, inefficient, and laborious, more pharmaceutical companies are looking to AI-based technologies to provide relief to regulatory and compliance teams. Among those leading technologies is NLP, which transforms a wealth of internal and external data into high-value, actionable insights, synthesising information from many sources to provide essential supporting evidence for business decisions.
