The RxView Blog

#5: How to Replicate a Clinical Meta-Analysis Study in Evidex

Overview: 

Traditionally, safety related meta-analyses have been costly, taken significant time to produce and can often miss relevant studies. Further, there has been no efficient way to test the outcome of those studies prior to initiation. This has led to a lot of unnecessarily wasted resources. 

Luckily, Advera Health with the help of machine learning, artificial intelligence, and data science is solving this problem for drug safety, epidemiology, and medical affairs departments of all sizes. 

We work with biopharma companies across the size spectrum.  When small and medium sized companies with marketed products first approach us, many of them have not implemented a software solution for signal management.  Why?  Many feel their case volumes are not high enough. Others believe they don’t have the right in-house resources. Still others have “a great spreadsheet that works just fine”. All of these excuses, err, reasons boil down to one thing: FEAR.

#5: 2018- The Year of Next Gen Drug Safety and Pharmacovigilance 2.0

Overview: 

We have a tradition in the RxView blog of starting each new year by asking if the year ahead will be “The Year of Drug Safety” or “The Year of Healthcare Technology”. We typically lay out a few thoughts on why the year ahead has the potential to be a big year.

I recently wrote an article for PharmExec called Pharmacovigilance Software is Having its “Salesforce” Moment. It discusses how the market for pharmacovigilance software is starting to catch up to other verticals through disruption by technological innovation. I argue that the barriers that were in place such as drug safety’s role as a cost center and the difficulty of accessing data are breaking down. And the result is that there are now choices in the pharmacovigilance software market that weren’t available just a few years ago.

After re-reading the article, I think there is an important, key point that got lost and could use further definition. The concept of the evolution of software from a “system of record”, to a “system of engagement”, to a “system of intelligence”, and why that evolution is so important.

In addition to asking questions around the value and validity of using social media monitoring for pharmacovigilance, we also often get questions around our thoughts on whether social media data are inherently biased. When I brought this question to the Booz Allen Epidemico data team, they educated me on the three dimensions of bias that come from different drug safety datasets: Patient reported outcomes, seriousness, and completeness. The graphic below shows how those three dimensions differ across social media, clinical trials, spontaneous reports, and EHR records.

One of the biggest fears that pharmacovigilance professionals have when it comes to using social media is that amount of work that it will create. How will you be able to take the time needed to "clean" the data and get it fit for analysis? Machines can be trained to identify posts with drug-adverse event combinations, but it is more difficult for them to be able to ensure the post is an accurate representation of an adverse event. Thus, Booz Allen's Epidemico team uses human curation to provide the most accurate data.

In recent years, the rapid development of “big data analytics” has created a surge within pharmaceutical companies to leverage data from the entire value chain to drive actionable insights. Although other departments within pharmaceutical companies have long been focused on utilizing data driven insights, modern pharmacovigilance departments are just starting to fully incorporate a data-and-analytics-first approach to signal detection, validation, and management.

In talking with current and prospective clients around Advera Health's partnership with Booz Allen's Epidemico social media monitoring data, we get asked a lot about not only the validity of the process Booz Allen goes through to cut through the "noise", but also about the value social media monitoring has for post-marketing drug safety surveillance and pharmacovigilance. In addition to highlighting the primer we put together, we also refer those interested to the numerous academic publications on the topic. Three core publications that Booz Allen has conducted in collaboration with regulators and industry serve as a starting point, and below is a summary of key points and links to the full publications. 

Modern pharmacovigilance departments today do more than process and review ICSRs. They are involved in the entire lifecycle of a drug, providing vital data points and analysis that inform everything from clinical trial design to commercial planning to post-market safety surveillance. In order to perform well, pharmacovigilance and safety science teams require access to an array of data and the analytics to make sense of those data. The insights gained from unique combinations of clinical and real world data drive signal detection, epidemiological research, and evidence generation, all of which support organization-wide decisions.

The problem is that drug safety insights are hard to obtain and teams often get caught in a "paralysis by analysis" trap.

It is now well established that the rapid expansions of the internet and computing power have opened up the use of social media and Internet forums for pharmacovigilance. These sources contain untapped, albeit noisy, safety and benefit information. As noted in Social Media Listening for Routine Post-Marketing Safety Surveillance, published in the journal Drug Safety, methods exist to reduce noise and make the data suitable for post-marketing safety surveillance. However, the use of these data to date have been constrained by limitations in how to best implement novel methods without disrupting traditional signal detection management and evaluation work flow.