For patient-reported adverse events to support clearer safety insights and improved outcomes, the fundamental problem of effective and consistent data capture must be solved once and for all. AI can help with this, but not in the way many think. The real opportunity is about how to get good data in, not how to make the best of poor data, and regulators could be doing more to drive this, says Daniel O’Keeffe of Qinecsa.
All pharma manufacturers and marketing authorisation holders have a duty to minimise the harm to patients that
And yet the process of capturing and qualifying real-world safety data is highly fragmented, and variable in the quality of its contents. Unless the pharma industry finds a solution to this challenge, it will continue to limit what it can do with that data. That includes the potential to harness AI to derive better intelligence. (Although some technology companies claim that AI is the answer to safety data fragmentation and chaos, this assertion is only valid if the base data is inherently good.)
Tracing the problem back to its source
As it stands, the safety data (adverse event reports) captured from patients and healthcare providers is incomplete and difficult to follow up. Diverse channels for reporting, and inconsistency in what and how much is captured, render findings hard to combine in a meaningful way – e.g. as the basis for actionable intelligence, blended with data gleaned from scientific journals, online forums, etc.
The first priority, then, must be to get better data in. It follows that the optimum time to capture maximum patient AE insights is at the time of initial reporting. Anecdotally, large pharma organisations report that barely just 10% of attempts at information follow-up (to fill in gaps in the narrative) are successful once initial details of any side-effects have been reported. So to miss this window, may be to miss those insights altogether.
Where the facilitator is a paid third party, for example someone contracted to deliver a patient support programme (a PSP vendor), it is particularly lamentable that such opportunities are being passed by. Regulators could be exerting more influence around original patient safety data capture and how this is done, with a view to building the richest possible understanding of each patient’s experience.
Unless the authorities mandate that better data is captured at source wherever possible, and dictate how this is channelled and managed, the drive for change will continue to be lacking. These requirements should extend to the vehicles for receiving and registering adverse event notifications. Where reporting might variously come via an email address, paper form or Word document, safety data collectors will remain compromised in their ability to share meaningful insights.
To capture a more rounded picture of an individual’s experience and wider health profile up front, data capture teams need better incentives, and to be better equipped, to collect and report more valuable data - especially if they are paid for this work.
Understanding where AI can actually add value
Today’s reality for pharma companies is a complex, multi-channel landscape through which relevant data can flow. Technology can help with this, and AI has a role here too – not to compensate where data is missing, but rather in making sure more of it is captured in the first instance.
Generally, it will be more effective to use AI to prompt good and comprehensive data capture (e.g. by guiding the user to provide additional information), than to apply tools later in the process once the opportunity has passed – although this too is a valid option if initial attempts were not possible or were unsuccessful.
AI could also be used to tailor and optimise the digital experience, e.g. for each inputter’s persona (e.g. patient vs HCP/pharmacist or CRO), their likely medical knowledge, their native language, the device being used, and so on.
An optimised digital experience for the reporter, with pertinent questions or prompts to capture all of the preferred detail, has been shown in pharma company deployments to enable 70% overall improved efficiency, including reduced follow-up.
The logical consequences of better safety data
Once better data is being captured, this can be put to beneficial use. Better data would provide a much clearer picture of adverse events and what may be contributing to them (such as drug interactions, pre-existing conditions).
Consider the high volumes of incoming data ready to be recorded around weight-loss drugs traditionally associated with diabetes treatment – those targeting GLP-1 and/or GIP receptors to control appetite. Side-effects may range from digestive issues to reduced muscle and bone mass. The opportunity to capture this information widely and draw trend information from it is rich and important.
With the current pace of drug innovation, and the shift towards more personalised treatments, every safety data point is precious – and needs to be treated as such from the moment of capture through to signal detection and analysis. Companies will also need to integrate systems and overcome data silos, allowing more insights to flow into all the relevant downstream systems - where they can be analysed and actioned, without the need for manual data re-entry.
All of this will support more accurate onward decision-making, boosting productivity and elevating patient outcomes.

