Monitoring in-country medical literature is an essential aspect of pharmacovigilance, providing an early pointer to adverse events in specific populations. Yet traditionally the process is highly resource-intensive, undependable in its output, with a small yield in terms of actual findings. That smart automation could transform delivery is a welcome development, says Biologit’s Jean Redmond.
Up to now, local (country- or region-specific) literature monitoring has been seen as a necessary but inefficient part of pharmacovigilance (PV). The practice is expected if not mandated by many health authorities, being the only sure way to establish that adverse drug reactions and safety signals published in such journals, web sites and/or print sources, are identified and reported. If gaps in routine monitoring are discovered during inspections or audits, this could have implications for ongoing licensing and sales, not to mention market confidence.
At a strategic level, local safety insights allow pharmaceutical companies (as well as healthcare systems) to respond proactively to emerging concerns in particular populations. They might inform labelling or guidance at a country level as appropriate, and help guide ongoing product development.
Critical, but onerous
Despite its criticality, local literature monitoring is tremendously inefficient in its current form. It usually requires dedicated staff at an affiliate or regional level, potentially with local language capabilities and local journal access. Despite the considerable volumes of content being reviewed, local monitoring may yield only limited safety information; errors/omissions are commonplace too.
Because of its resource intensity, local literature monitoring is frequently outsourced to clinical research organisations. The process typically involves monitoring a diverse range of designated sources, listed in multiple, unwieldy Excel spreadsheets where findings are also logged. Assigned teams are expected to monitor several thousand different web sites on a weekly or monthly basis.
The challenge is compounded by substantial variances in the literature format, literature access issues and language barriers. Local sources tend to lack consistency in format, indexing and language, making it difficult to implement a simple unified process, while many local journals require paid subscriptions or may be only available in print.
Additionally, regulatory reporting timelines tend to vary by country, something else that has had to be tracked manually to ensure respective adherence.
All of these challenges above present a regulatory risk, as well as a risk to patient safety. This is due to the potential to miss safety events.
It is a situation that will only intensify, too. With the growing focus on specialty drugs including more personalised and targeted treatments in oncology and for rare disease, including new therapeutics such as CAR T-cell therapies, strong drug safety/PV oversight is essential.
It is for all of these reasons that the pharma industry and its service provider community are looking to next generations of automation technology for an answer.
Advanced automation offers a big part of the solution
So what is prompting process innovation? New technology enablement, involving large language models (LLMs), is proving instrumental firstly in structuring data – enabling “normalisation”, unification, centralised management, and governance of materials, as pharma transitions to “data-first” ways of working.
In parallel, advanced “crawling” techniques are transforming automated browsing, “scraping”, and indexing of content from target web sites and publications. AI can then add a further layer, making it possible to search all of that content very quickly and identify all relevant safety events on demand.
Of course, where patient safety is concerned, there will always be an important role for human oversight and process governance. (Technology-assisted human ingestion is another option, where companies are more hesitant about immediate technology reliance.)
Persisting without automation is hard to justify now, though. Most pharma companies have come to accept that, unless they buy into technology-enabled process innovation, they will struggle with continued operational viability in this challenging world economy. With easy, rapid access to the data they need, on the other hand, PV scientists could focus on the higher-value activities that form the core of their role, even as medical literature volumes explode.
The bigger picture beyond PV
As companies transition away from laborious manual processes in their literature monitoring, the strategic potential lies in the new, richer, data-driven insights they will gain about safety trends.
More broadly, this is an opportunity for companies to better understand the safety trends around their drugs – and at a more discrete level. As well as informing ongoing drug discovery and development, early population-specific insights could also inform the respective healthcare system and patient journey in a given region, with wider societal benefits.
A Biologit white paper further exploring this topic, can be downloaded here
About the author
Jean Redmond, PhD, is COO at Biologit. She is a scientist with 10+ years’ experience in consulting, strategy and general management gained by working with multiple life science offerings and teams at a global clinical research organisation (CRO). Biologit is a specialist in advanced, technology-enabled safety surveillance solutions for life sciences.
