Tangible applications of GenAI in pharma R&D today: making light work of AE case intake

Pharmacovigilance processes are designed to uphold the safety of marketed human medinical products over time, once authorised for patient consumption, but as the ocean of available data continues to rise in volume, the task of discerning and acting on important signals is becoming ever harder. It’s odd then that approaches to post-market Safety monitoring have changed little in decades

First there’s the increasing array of formats through which cases come to light, not to mention the proliferating range of channels. Current approaches don’t take into account the actual contents of a case either. This means there is no discretion to allocate teams’ bandwidth according to a potential case’s complexity or risk.

Superhuman ability

In the context of pharmacovigilance, technology-enabled process automation has long promised to transform the speed, efficiency, and accuracy of adverse event (AE) case intake and triage, by capturing and assessing relevant Safety signals wherever and however these come to light.

While early automation systems had to be highly structured and painstakingly trained to recognise every possible format and variant of how important data might show up, Generative AI (GenAI) and Large Language Models (LLMs) are inherently more discerning and quick to learn. In early pilots, data extraction accuracy and quality have exceeded 90 percent, and overall efficiency gains related to the intake process have topped 65 percent. These rates will improve sharply over a very short period of time, too, as they continue to be exposed to cases.

The intensifying hunger for change

Advanced automation solutions that transform the data collection part of the AE case intake process are being welcomed in an industry desperate for a modern, more efficient way to execute case intake/safety data collection. That’s as pressure mounts to accelerate analysis times despite rising data volumes. Today, more than 75% of biopharma R&D organisations already use some form of advanced automation within daily processes today, and more than 70% plan to expand business process automation over the next 18 months[1].

Companies’ appetite for viable solutions has intensified in line with a maturation of AI-powered process automation technology to the point that the technology understands so much more about what it is looking for (irrespective of format), and what to do with it (compared to early robotic process automation).

GenAI technology, using LLMs, can quickly identify and infer what’s relevant and important and reliably summarise key findings for the user - and even extrapolate from them to make predictions. Specialised applications can be developed too, that can apply GenAI-type techniques - contextually -to data they haven’t seen before.

This significant leap forward has some pharma companies testing GenAI AE intake solutions under the watchful eye of their Safety professionals. The ability to simply instruct a system to “Scan X document for Y contents” paves the way to faster, higher-quality extraction of more relevant data, reducing the risk of omission while improving downstream efficiency.

A raft of potential benefits

A large element of the business case for harnessing GenAI in AE case intake management comes from the scope for handling first-line capture and processing of very high volumes of data – freeing up more of Safety professionals’ time to analyse the findings.

Added to this, GenAI removes human limitations such as fatigue, mental overload, distraction, data blindness, and unconscious bias. An AI-powered tool can draw on the findings of millions of prior cases and assessments, to make credible predictions and unbiased assessments about causality, based on probability.

Looking ahead

Beyond AE case intake, there will be other powerful use cases across Life Sciences R&D Safety and Regulatory operations, so it will be important allow for additional applications in the future (for instance by deploying an enabling ‘platform’).

Strong next contenders for GenAI/LLM treatment include real-time PV assessments and associated decision-making (e.g. the earlier identification of unexpected benefits/discovery of new indications); harnessing international Regulatory intelligence to transform marketing authorisation applications and maintenance; and clinical trial modeling, reducing the reliance on traditional clinical studies.

A recommended first step toward advanced automation would be to break down how processes are currently managed, the core requirements driving those processes, and where any pain points lie. The next priority should be to review and rewrite standard operation procedures so that they can evolve with and be improved by advanced technology, both today and in the near future.

[1] ArisGlobal’s 2024 Industry Survey Report, Life Sciences R&D Transformation: Ambitions for Intelligent Automation & Today’s Reality,