January/February 2024 • PharmaTimes Magazine • 20-21

// DATA //


Healthcare flare

Proactive signal detection based on real-world data is a welcome step change in post-market drug safety monitoring

Image

Safety signal detection in post-market drug monitoring has changed little since the discipline was first introduced following the 1950s thalidomide tragedy.

But now smart new technology applied to robust, standardised real-world data, from sources including electronic medical records and healthcare claims, is set to make proactive signal detection a reliable reality. ArisGlobal’s Elizabeth Smalley explains.

Safety signal monitoring has changed little from when the practice was first introduced around 70 years ago in response to the thalidomide tragedy.

Systematic monitoring of adverse drug reactions was one of the formal regulatory responses to the international event which affected more than 10,000 babies.

Since then very little has progressed in the discipline of signal detection and analysis since the early 1960s, other than to remove the reliance on paper-based reporting.

Outside of the clinical environment, with the inherent limitations of its strict controls, adverse event monitoring still relies heavily on patient and clinician reporting, for instance. And, yet, even today too many adverse events go unreported (up to 95% in the worst cases).

Even once submitted, Individual Case Study Reports (ICSRs) take time to process before they are used in signal detection. Analyses of medical literature, another PV channel, also inevitably involve a time delay, while scouring of online forums yields too much noise.

Vigilance requires responsiveness

If safety signal detection, as an integral part of pharmacovigilance, is to fulfil the goal of keeping patients safe, the discipline needs to be smarter and more responsive.

Fortunately, the latest intelligent analytics technology, along with efforts to standardise and democratise access to real-world data (RWD), is making this a reality now.

Advanced analytics technology can filter for causal and sensitivity to substantially reduce signal ‘noise’, with 40%+ more accuracy than traditional signal detection methods.

This means that professionals will be able to distil precise adverse event insights directly using robust real-world data from electronic medical records and healthcare claims, boosting drug safety and driving new efficiency for drug developers.

Shifting signal detection closer to the patient will help address gaps and lag time in adverse event reporting, reducing marketing authorisation holder (MAH) risk.  Indeed, the benefits will be widely felt right across the healthcare ecosystem – by patients, drug development companies, regulators, and clinicians.

Proactive, hypothesis-free signal detection along with improved signal strength is shown to reduce false positives and detection signals earlier.

The incorporation of real-world data, meanwhile, means signals are detected even faster and with impressive precision – the equivalent of a thermometer quantifying the progression of an illness, or a financial credit score objectively assessing an individual’s economic health/risk, enabling robust new protocols and better overall outcomes.

Making smarter connections

So, what’s making all of this possible?

At an AI level, large language models (LLMs) are transforming the precision with which Safety teams can distil insights from vast data sets, quickly learning and progressively honing their knowledge of what to look out for and what to discount.

The technology is so intuitive to use that Safety teams have less need for the intervention of epidemiologists or data retrieval experts, now being able to perform a deeper level of causal analysis themselves.


‘The incorporation of real-world data, meanwhile, means signals are detected even faster and with impressive precision’


LLMs are priming the pharma industry to easily embrace all kinds of AI – something that was not possible even three years ago. This is likely to drive extensive adoption of proactive signal detection now, delighting regulators, clinicians and patients alike.

Provided there is an appropriate interface, and that the right data preparations have been made so that Safety teams cannot be misled by the findings, Safety professionals can perform their own investigations on the fly, in a highly repeatable way.

Commercial benefits

The benefits of proactive signal detection, via AI-sharpened analysis of extensive and robust real-world data, in conjunction with ICSRs, are broader than simply faster speed and greater accuracy.

As correlations are detected earlier and with improved precision, drug developers will be in a position to spend more time on higher-value activities including innovation in drug discovery, and on delivering safer drugs to patients, sooner.

Meanwhile, safety-based communications will become much more targeted. Instead of stating generically that a drug may increase the risk of heart attack, the advice can specify that this risk applies specifically to women between the ages of 30 and 60 who have a pre-existing heart condition.

This opportunity goes hand in hand with the growing focus on personalised medicine.

The same mathematical principles used in adverse event monitoring also support signal detection in drug repurposing, potentially presenting new commercial opportunities to drug developers as previously unknown and unexpected positive correlations are discovered.

In the context of a benefit-risk profile, this is an opportunity to focus as much on the benefit as on the risk profile, and to grow the commercial potential of a drug. In this context, safety has an unprecedented opportunity to shine as a strategic partner to the business, rather than merely a cost centre that exists to contain risk.

In an industry now so keen to innovate in all aspects of drug development and delivery, next-generation signal detection is emerging as an exciting field to watch.

Crucially, these are possibilities that leading pharma organisations are already exploring today, certainly in the context of adverse event signal detection.

As a result, patient safety will go up, teams will be freed up to spend more time on drug discovery, and more time on drug repurposing, ultimately leading to more safe and effective medicines being put into the hands of patients much sooner.


Elizabeth Smalley is the Director of Product Management, Data & Analytics at ArisGlobal.
Go to arisglobal.com