Moved by Metrics Pharma,Predictive Models Pharm3r on the Open FDA Data Initiative, AE Reporting and Post Market Surveillance

Pharm3r on the Open FDA Data Initiative, AE Reporting and Post Market Surveillance

Drugs and Devices: What Matters Most is the Patient
“I got an email from someone who was neither a doctor, nor a payer, nor an insurance broker, but just someone who had read our piece on the catheter breakage.  She wrote that she had been a patient for many years  and absolutely dependent on indwelling medical devices.  She read our piece on how we are able to identify problems early, and she realized how incredible it was – we were truly promoting patient safety and welfare. I sent this woman’s email to the entire team, with a note saying ‘this is why we get out of bed in the morning’,” shared Libbe Englander, PhD, Founder, and CEO of Pharm3r.

Dr. Englander formed her company just five years ago. Pharm3r (pronounced “Farmer”) (@Pharm3r) actually cultivates very large datasets by accessing multiple sources of information on end-user experience of medical products, allowing people to track adverse events and compare product effectiveness.  A software company at its core, proprietary programs use natural-language processing and artificial intelligence to mine, extract and combine data. This allows companies to find trends in adverse events, and identify product problems and patient sentiment. Having had the pleasure to meet with Dr. Englander in her New York  office, here is a transcript of conversation, edited for clarity.

Where do you think Pharm3r has made the most impact on public health? 
Dr. Englander:  It’s hard to narrow down–we’ve been having a busy and brisk couple of years!  We just put out a case study on catheter tip breakage, Pharm3r Case Study: Predicting Medical Device Recalls.  It’s one of many, but because it was just published, I think it makes for interesting reading.  Cook, voluntarily recalled their Beacon® Tip catheters. They felt that there was a higher-than-acceptable amount of tip breakage.

We were curious about how the catheters still on the market compared, went to our system and immediately pulled up our data. We ran it through Boomerang NLP™, our natural language processor.  It turned out that Angiodynamics’ catheter had a  higher rate of tip breakage.  Subsequently, that product was recalled.

NB:Dr. Englander also shared that they will soon be publishing a paper on the TAVR (Transcatheter Aortic Valve Replacement) and MitraClip® clips both for valve disease treatment.  Pharm3r will compare their data with highly curated, very expensive patient registries. So far Pharm3r data has been replicated in these registries, which serve as a good quality control.  Importantly, they will soon be able to share the comparative effectiveness of each of the TAVR valve products, which are not publicly reportable from registries.  Dr. Englander: “Many companies are making, in some cases, lifesaving instrumentation and drugs, but there are side effects with everything.  The sooner they are detected, the sooner an engineering and corrective measure can be instituted.  Companies are very interested in making sure they are the first to know.”

How does one go about reporting an adverse event in MAUDE and FAERS?
Dr. Englander: Anybody can report an event – a doctor, a patient, family member, a concerned citizen- and that, in a sense, is the real power of these databases.  It is tremendous that there is a way that those voices can be heard. I think it is so significant that anybody can fill out a MAUDE (Manufacturer and User Facility Device Experience) report or an FAERS (FDA’s Adverse Event Reporting System) report.  They are so easy to do – they can be done electronically, by hand. Our job as a company is to translate that voice into meaningful information.  We feel that theses databases capture the end user voice in a very democratic, wisdom-of -the-people fashion.

How has your technology and products improved adverse event reporting?
Dr. Englander: One of the things that we can do is start looking with natural language processing at the MAUDE narrative, which is a very rich source of information.  You not only have a huge amount of structured data on the product, which is submitted by a patient or medical professional, but also often a very large ad important narrative text that is associated with each one of these reports. We have a patent-pending natural language processor, which allows us to read effectively those 5 to 6 million MAUDE reports. We are able to look at product problems and adverse events in a precise and sophisticated fashion.  If you are a patient and about to get a valve replacement, using our product, you can now know which valves are associated with adverse events.  Each report is accessible to the public, but to put them together and do a comparative analysis, you need our system.  Our best-use case is to inform patients, doctors, payers, governments where there are trends, adverse events and comparative effectiveness that are meaningful.

What do you think are the advantages and limitations of the OpenFDA Data Initiative?
Dr. Englander: The OpenFDA initiative,  requiring and encouraging people to report adverse events in the FAERS database for drugs and the MAUDE database for devices, is, I think,  an extremely credible and well-intentioned project.  The Open FDA is a great initiative is to start playing with. The idea of saying ‘let us try to put an understanding of the end user experience in everyone’s hands’ is a well-intentioned one.  However, the current iteration of the OpenFDA,  is also deeply flawed, as it does not reliably reflect the underlying dataset for a couple of reasons. There is a lot of miss-matching of names, carelessness in terms of how things are dated, and a lack of suppleness in extracting the exact adverse events.  We wrote a white paper, OpenFDA, raw FAERS and Pharm3r’s PandoraPlus™  that deals with this in depth.  On a few time series test cases, the time series were really not representative of the underlying data.  As a sophisticated computer science company, we take the raw data sets and look at the underlying data in a much more nuanced, careful way.

Has Pharm3r been engaging with the FDA on Post Market Surveillance? 
Dr. Englander: Yes, and I have been very impressed with the people I talked to [at the FDA] so far.  Their challenge is that they don’t want false positives. They don’t want to yank things off at any bad signal.  I feel they are very much trying to do the right thing. They are  exploring the best way of doing post-market surveillance.  It is an important problem.  The better the technology you have, the faster and the more accurately you can see the problems.  We are giving a webinar on the September 20th under the auspices of the FDA to discuss our technology on this.  I think it is a public health issue.  It is a comparative effectiveness payer issue.  What we do is really critical. A lot of our work is for product liability insurance companies. They are insuring the companies making these products, so it about how you price that risk and how you take that risk.   Ideally, the insurers and brokers are in a position to encourage these companies to be even more proactive about avoiding product problems.  I really think we are at a moment in time.

Pharm3r  is a computer science company that is linked to sector expertise looking at medical products. They help their clients think about effectiveness, risk, pricing models, risk models and ultimately the effect on the patient and the end user. The company has been successful in identified major datasets and has done a highly competitive job about collecting, and correlating and analyzing them. They do everything from building predictive models to looking at trends and comparative product effectiveness. To learn more about Dr. Libbe Englander, Pharm3r, and their products click here.

 

Related Post

Applying Propensity Score Methods with Elizabeth Stuart PhD Part 1 Electronic Health Records Study DataApplying Propensity Score Methods with Elizabeth Stuart PhD Part 1 Electronic Health Records Study Data

By Sarianne Gruber Twitter: @subtleimpact A statistician by training, Elizabeth Stuart, PhD is a professor of Mental Health, Biostatistics, and Health Policy and Management at Johns Hopkins Bloomberg School of Public Health,