how to process data
By Axel Hagel, practice lead, PV & RM services, IQVIA
Life science data, especially security data, is exploding.
Estimated pharmaceutical data increase at rate of 36% per annum. This is more than other data-driven industries including finance (26% YoY) and manufacturing (30% YoY). This increase is partly due to digital data sources and new pharmacovigilance methods that have become popular during the pandemic in an effort to accelerate vaccines to market.
As a result, currently, pharmacovigilance teams must manage skyrocketing amounts of data from multiple data sources, with more than 250,000 adverse events come from US citizens alone each year. Safety teams needed a more efficient way of managing safety caseloads and effectively using available data to their advantage. Advanced data analysis and automation technologies, such as artificial intelligence (AI) and natural language processing (NLP) simplify adverse event intake and processing (AE) activities.
A simpler approach to AE intake
Pharmaceutical and medical device safety is a complex process, and it becomes even more complex as the volume of data pulled from multiple sources increases. To add to the challenge, regulatory agencies around the world have different requirements around data collection and use, which life science companies must comply with, and these regulations are constantly being updated and revised based on new trends, technologies and findings.
How can life science companies effectively address these multiple challenges? They need to take a step back and evaluate their approach to safety and determine how to implement it in the current regulatory and data environment. Companies must consider how to optimize and integrate safety processes by leveraging the game-changing technologies available today.
However, strategic technology deployment is critical to the success of any transformation initiative. Companies must first understand the goals they want to achieve through transformation and optimization. These goals will vary from company to company; however, in general, having the ability to access safety data and the correct case information quickly will be a primary concern.
Manual activities are a major bottleneck for data management and efficiency purposes, resulting in higher operating costs and lower quality of end result. For many organizations, more than half of all safety processes are performed manually, including the collection and extraction of data from one source or format to another. Now, as data volumes increase and complexity makes manual activities time-consuming and error-prone, traditional methods of identifying AEs, contextualizing case information, reviewing cases, and processing information are no longer useful for achieving the end results life sciences organizations require: Remain compliant and efficient in safety operations.
Adopt productivity-boosting technologies for case processing
To overcome the blockade of manual activities that impede safety efficiency, companies need to apply technology that supports automation. Automating the receipt and management of each collected AE simplifies the collection process. Furthermore, advanced data analysis technologies, including AI and NLP, ensure data consistency and accurate collation regardless of data type or source. This strategy reduces the time spent analyzing and processing case information and eliminates the risk of human error, which can waste analysis of safety data if left untreated.
Various AI-based technologies and web-based strategies are involved in simplifying and automating case processing. When strategically implemented, this technology enables advanced case processing and better decision making.
Life science security data comes in many forms these days, including voice and text messages.
Conversational AI, which understands how to mimic human speech patterns and process conversational text or voice messages, can drive always-on agents to monitor potential AEs around the clock.
Conversational AI agents can identify and report AEs or pharmaceutical quality commitments (PQCs). Conversational AI agents integrated with contact center operations ensure seamless handover to human workers when cases need to be escalated. During handoff, AI agents can pinpoint exactly why the AE data was improved, eliminating delays caused by manually listening to audio files for quality checks and data extraction.
NLP, based on AI technology, enables automatic analysis and processing of unstructured text. Unstructured text, often culled from web sources, literature, drug labels, or handwritten notes, can take hours to manually clean and analyze. The abundance of unstructured text files and sources makes any attempt to review the information manually futile.
In terms of safety case intake, NLP ensures any relevant AEs found in unstructured text are quickly and accurately identified. It can then AE encode, further reducing manual workload and ensuring consistency.
AI search engine
Sorting complicated data, let alone finding a special needle in a pile of data, takes unnecessary time if done manually. The diverse datasets managed by today’s safety teams require AI-powered search capabilities to enable rapid discovery of AEs, PQCs, and other risks. When left solely for human analysis, these risks can go unidentified if they are buried in piles of security data.
While it may seem easy, enabling such a search function requires a combination of AE signal detection, entity extraction, and NLP analysis. However, when done right, life science security teams will find that AI search engines increase speed and quality while reducing compliance risk.
Intake management tool
AI, NLP and automated translation tools help safety teams categorize, code and process AE data at the intake level. Regardless of the data source (forms, email, E2B, literature, etc.), intake management tools simplify the receipt and management of safety data. This significantly reduces data entry costs on case receipt and pays further downstream when cases are processed and reviewed (in activities including data validation, triage, duplicate checking, and redaction), as it is managed by the retrieval tool.
Guided web forms
One of the most helpful techniques for simplifying the capture and processing of safety cases is actually not incorporating AI technology or automation. Multilingual guided web forms literally guide the user through the required information input. This form allows everyone from patients, to healthcare providers (HCPs), to patient support programs (PSPs) to report an AE. As the form guides the user through the data entry process, ensuring all relevant information is included, the need for follow-up to verify data is eliminated. In addition, the multilingual nature of these forms ensures that any data received complies with local privacy regulations.
Simplify complex case processing challenges with automation
This strategy has yielded impressive results at several pharmaceutical companies, including one company that successfully utilized the technology to process more than 450,000 cases in various regions, including the US, EU and Japan. As a result, first-time quality increases by 20%, while data entry and quality assurance costs decrease by 35-65% depending on the source of cases.
When combined and strategically deployed, conversational AI, AI-based search engines, guided web forms, intake management tools, and NLP technologies enable pharmaceutical and medical device safety teams to streamline operations and reduce costs associated with ensuring patient compliance and safety. This will be an important milestone in determining which pharmaceutical companies can successfully keep up with rapidly changing regulations, separating compliant organizations from those at risk of being impacted by regulatory non-compliance.
Axel Hagel has over 21 years of experience in the life sciences industry, specializing in drug safety applications in North America, Europe and Japan. He has experience and implementation skills for the Argus Safety Suite, including Argus J, and is recognized in the drug safety sector as a leader in the pharmacovigilance industry.