From soaring caseloads to broadened biopharma territory, the unequivocal case for advanced tech use to transform pharmacovigilance

Ongoing drug safety monitoring is critical not only for regulatory compliance and risk management but also to maximise the benefits of products for patients.

This applies even more so as the industry diversifies into new therapy areas where longer-term side effects may be difficult to predict. As drug development ambitions rise, and as overall adverse event case processing workloads soar, a smarter approach underpinned by AI and advanced automation is becoming essential, says Qinecsa’s Adam Sherlock.

Up to now the value added by pharmacovigilance, beyond satisfying regulatory demands and managing risk, has been somewhat overshadowed by the need to cope with rising workloads in the context of a challenging economy and finite budgets.

The main preoccupation has been to find ways to deliver more for less via optimal outsourcing arrangements and targeted use of technology.

As brands diversify and add more novel and ambitious therapy areas to their portfolios, however, a further driver for honed PV practices vies for consideration.

A whole range of important new therapies and drug applications is entering the market now, supported by regulators who are working hard to shorten their paths to market without compromising patient safety.

These propositions include GLP-1 receptor agonist/weight loss injections (WHO plans to officially support their use to treat obesity in adults), as well as the use of messenger ribonucleic acid (mRNA) technology in approaches to cancer.

That’s in addition to the COVID-19 vaccines, developed and approved at speed five years ago and given to a large proportion of the population worldwide – which still need to be closely tracked for new or incremental adverse events.

In the context of new modalities and novel therapies with less predictable long-term impacts, there is a heightened need to detect and report issues and emerging patterns swiftly. This in turn is placing new emphasis on technology-enabled PV transformation as a means to hone accuracy, precision and speed in addition to operational efficiency.

It is in the context of these converging demands that AI is starting to make its mark as a mature and viable solution to AE case processing.

The need for pharma companies to diversify as a means of new brand differentiation and long-term growth, added to their already soaring AE case volumes, leaves them with no real choice about embracing next-generation, AI-driven process automation.

The majority of PV scientists today are highly overstretched. They are also difficult to recruit or replace, while their skills are needed (yet are not available to be deployed) at a more strategic level.

At the same time, intelligent automation technology is advancing at speed. Tangible and robust AI solutions specifically designed for PV are becoming available now, and many of the major pharma organisations are testing them with encouraging results.

They have been observed to reliably handle large volumes of data, extract key information from various sources and even detect subtle patterns that might be missed by human reviewers. In the US, the FDA estimates that implementing AI in PV has improved the detection of potential drug risks by over 25% since the technology’s introduction.

Not only has AI’s acceptance in life sciences and in a PV context been established, companies are realising that the sooner they can bring in the technology, the more they stand to gain – not least because AI’s accuracy and efficiency improves sharply with exposure and training.

The right approach to implementing AI in an AE case processing context will depend on the current state of affairs at the respective company. Much will be dictated by a company’s existing PV ecosystem, the volumes of work it underpins, and the existing technology infrastructure that’s in place, for example.

So, while PV technology vendors might be promoting the latest functionality and promising much in terms of the efficiencies it represents, pharma companies will need to determine how well this will fit with what they have and how they work today.

They must also be clear about the tangible benefits they expect to derive from deploying advanced technology, including cost reduction, improved productivity, honed accuracy and faster reporting.

Large pharma organisations, processing many hundreds of thousands of spontaneous AE cases each year across extensive and diverse portfolios, are likely to gain the most from having access to advanced technology to ease the PV load.

Yet, even here, it isn’t just the scale of the operation that will determine the best path to AI use. Retiring legacy safety databases can be onerous, so implementing AI may involve sophisticated workarounds and wrap-around software; giving users a single, simple, intuitive interface or portal, and creating a layer that ringfences the core safety database and extends its return on investment.

For organisations with more modest product portfolios, immediate PV pressures are more likely to revolve around limited internal resources, scalability and associated challenges with meeting AE reporting timescales in key markets.

Here, the best route to embracing AI may be to establish a digital-first capability – beginning with the inbound AE case capture process, ensuring that this is digitised across all supported channels. The more that cases can be captured digitally at source, the greater the potential impact of AI in their assessment and processing.

Whichever route companies go down in transforming their AE case processing capability, the priority should be to actively take steps towards this now – and not to overlook the strategic benefits on offer (beyond the expected step changes to operational efficiency).

Supported by the right technology, the PV function could become a more strategic partner in drug development and product life cycle management. PV-driven insights could inform new studies, for instance: ‘In England, reports of pancreatic issues linked to weight-loss injections have triggered a new study into side effects of the treatments’.

They could also help pinpoint new use cases for existing drugs for further exploration, distilled from records of unexpected side benefits. Targeted use of AI and advanced automation could help activate all of this potential.