September 2024 • PharmaTimes Magazine • 28-29
// AI //
GenAI heads up
Creating better regulatory submissions – could AI take the strain?
It’s only a matter of time before generative AI (GenAI) will be charged with automatically generating entire regulatory submissions from scratch – and bolstering their impact based on what’s gone before.
Already in its relatively short existence, GenAI technology has come a long way.
Today, it is actively transforming everyday pharma regulatory and safety processes, based on its ability to very efficiently digest, assess and summarise key insights and findings.
These emerge from across vast, diverse reserves of content and data, both historical and evolving.
Early pharma pilots in a regulatory affairs context have seen GenAI pre-empt agency queries and build stronger marketing authorisation applications, as a powerful process accelerator and productivity aid.
Across 23 different languages, up to 12 fields of data have been extracted with 90% accuracy – with 80% faster processing and three times fewer handovers than without GenAI use.
The technology is also demonstrating powerful potential in monitoring and proactively using the latest global regulatory intelligence, e.g. as part of regulatory impact assessment when health authority requirements change.
Here too pilots have yielded 90% accuracy, with 80% faster processing, and in this case half the handovers (versus manual regulatory intelligence lookup and intervention).
Tip of the iceberg
Within the next two years, regulatory teams will use GenAI tools to compile and crosscheck entire submissions automatically, with a human-in-the-loop quality review from regulatory professionals requiring a fraction of the effort expended today.
Large pharma organisations generate 600-800 submissions per month. Even a very modest time saving (say 1-2 hours per submission) could make a substantial difference to associated resource allocation.
And savings could be much greater than that, once GenAI is fully harnessed to automate the collation and assembly of content – extrapolating from initial regulatory use cases of the technology.
Among the enablers of this automation leap, to the creation of complete submissions, are GenAI’s accelerating pace of advancement, its steady maturation and the technology’s rapid acceptance.
Transformers
Already today, GenAI technology is being used widely and with confidence to analyse and infer meaning from data and content in a wide range and formats, and distil what is needed into whatever the desired new format for the target context.
The next wave of developments will build on all of this progress, to enable end-to-end process transformation.
In a marketing authorisation submissions context, as the ability to distil and crosscheck information across all modes and formats (tables and diagrams, as well as text in any language) is honed, so optimised GenAI tools will be able to consult and verify with the latest regulatory intelligence on demand.
This validates what content is required and verify how this must be presented, with little to no input from human professionals up to the point of review.
‘Within the next two years, regulatory teams will use GenAI tools to compile and crosscheck entire submissions automatically’
Identifying & building
These targeted GenAI applications will be able to identify and draw from the latest correct sources, to collate and repurpose the relevant information and fill the respective submission outline.
This will automatically involve crosschecking with the company’s regulatory information management (RIM) system, assessing what has previously been submitted, to ensure that the new submission is accurate and consistent.
Through all of this lightning-fast crossreferencing (which will ensure that the correct excipient/ingredient information has been extracted from the latest documentation for instance), GenAI will not only expedite and reduce costs associated with submissions compilation. It will also improve the quality, accuracy and success rate of submission updates, boosting the company’s track record with regulatory agencies.
In the meantime, skilled teams will be free to focus more of their attention on scientific work – activities that add more value for the organisation, and are more rewarding for those subject experts.
Recognising & accommodating
In addition to fulfilling the demands of agencies in mature regulatory markets such as the EU and North America, advanced automation in regulatory submissions generation will transform the efficiency of dealing with less developed markets, which together account for a sizeable proportion of the future global life sciences opportunity.
Growth in pharma sales in emerging markets is set to accelerate over the next decade, with medicine use in Latin America and Asia expected to rise faster than other regions over the next five years.
Many of these markets still rely heavily on non-electronic files, for submission to authorities whose requirements are less standardised.
The ability to streamline associated submissions with advanced end-to-end automation promises to be very powerful here, in helping companies navigate the differing requirements, deduce ‘what good looks like’, and swiftly collate and format what’s needed for optimal impact.
Laying foundations
With all of this potential on the horizon, life sciences organisations need to get to grips with GenAI technology today – to get a feel for how far GenAI can go, how quickly results can be honed, and how much time and budget this could buy back for hard-pressed regulatory teams.
Further opportunities for GenAI in a regulatory context, for instance, include more efficient and effective maintenance of labelling compliance internationally, across the product life cycle – again boosted by automated, GenAI-enabled cross-referencing.
Simply adding a GenAI capability is no magic bullet, of course. In parallel, companies will need to bolster their regulatory intelligence knowledge bases (e.g. with the latest information on emerging/developing markets and their submission requirements).
They must also continue enhancing and unifying their product data. The stronger the assets that GenAI can draw from, the greater the potential for deep process automation.
Agnes Cwienczek is Director of Product Management at ArisGlobal.
Go to arisglobal.com
PharmaTimes
PharmaTimes is the UK’s leading pharmaceutical magazine, tracking the trends and issues that affect the industry here in the UK, in Europe and across the world. We deliver independent, authoritative and trustworthy content through impartial, balanced and informed opinion and analysis.