Capturing the Inherent Visual Authenticity of Solid Oral Medications


Four years ago we faced a serious problem. Our team of computer vision scientists was developing a medication adherence monitoring system that could identify tablets and capsules using only an image taken with an iPhone. We quickly learned that due to manufacturing variation there are often several visual “variants” of each medication in circulation – substantially increasing the complexity of this task. However, the recognition that this visual variation was systematic and could be statistically captured through a straightforward sampling process would lead to the development of MedSnap’s highly scalable system for precision product authentication.

Systematic variation can be modeled and used for authentication

Early on we recognized that if you’ve seen one pill, you’ve seen one pill. At the lot or batch level, individual instances can have slight variations in texture or imprint. However, using images of 100 pills from a lot we create composite statistical models which generalize across the lot, and in most cases across that entire production line. Variation between lots from the same line, albeit rare, are accommodated through more frequent lot sampling.

Using the iPhone camera our effective resolution at the surface of the tablet or capsule is 415 pixels per square millimeter. With our Snap Surface background we can measure size and shape to within 0.1mm and differentiate over 250,000 shades of color. Therefore our ability to measure size, color, imprint and texture are well within the tolerances of the production equipment making the product.

The net result is we capture the small unique visual characteristics of a product that make it distinctively authentic. Often we can differentiate authentic products made at different facilities – and attribute them to their site of origin when necessary.

Sampling visual output as a part of lot QA

Dissolution and other tests are performed at the end of the manufacturing process. Visual assessment using our VR testing app can be easily added to this workflow – it takes less than a minute. Any failures represent a statistically significant visual change in the product. QA staff can then decide whether to add this new variant to the set of statistical models which define authentic for that medication, or reject the batch. In this way the definition of authentic is described by a set of models which can be continuously updated and expanded across an entire network of production facilities, keeping pace with changes in tooling or excipients.

Counterfeiters are surprisingly precise but not accurate

Like any manufacturer, in order to make a margin counterfeiters must scale their operations to produce product in sufficient quantities to meet demand and with visual quality high enough to fool a non-expert on inspection. We also sample counterfeit products and compare their visual relatedness. Surprisingly, some counterfeit products show visual consistency across and within samples rivaling that of authentic products. Visual clustering therefore can provide a “fingerprint” of these operations, quantify the product they have produced, and provide important intelligence for investigators.

It can be intimidating to recognize the industrial production capacity that many counterfeiters possess. However, given that two authentic production facilities cannot easily make pills that look exactly the same due to slight differences in equipment, tooling, and excipients, it would be extremely difficult for someone outside your company using different materials and equipment to produce a perfect visual counterfeit. To date we have not found an example.

Setbacks can help you take a big leap forward

The systematic variation in the production process for solid oral medications was at first a big problem for our team, but tackling it led to insights which have allowed for the creation of tools that utilize this variation to authenticate the physical product. With this unique, novel approach there is no need to modify the product to capture its inherent authenticity.

Email this to someoneShare on Google+Share on LinkedInTweet about this on TwitterShare on Facebook

Shazam for Pill Authentication

Back in 2000, audio engineer Avery Wang invented the technology inside Shazam, an app that turns your smartphone into an expert in “Name That Tune”. Far from a frivolous app to alleviate the frustration of having a song’s name on the tip of your tongue, Shazam has revolutionized the way music is promotedwritten, and consumed. Similarly, advances in computer vision along with the speed, capacity, and camera quality of smartphones now make it possible to definitively authenticate pills simply by Snapping a picture – without product modification. Now any consumer, pharmacist, clinician, investigator or QA engineer  – anywhere – can precisely validate the authenticity of solid oral products. How will this change supply chain security and its contribution to the value of pharmaceutical products?

A Secure Supply Chain Becomes a Consumer Marketing Advantage – Especially in Developing Markets

Developing markets are particularly challenging – yet they represent huge growth opportunities. Consumers in markets with a high prevalence of counterfeits are well aware of the problem and can be hesitant to spend hard earned money on brand or generic medications they see as risky. Consumer authentication of the physical product is a huge marketing opportunity and potential differentiator.

Authenticating Returned Goods

A counterfeiter’s backdoor to easy profitability at your organization’s expense is to return fake product for a refund. Given about 2% of all product is returned, there is significant profit to be made – especially with popular brands. Until now there hasn’t been a scalable or practical way to authenticate returned physical product. Combining physical product assessment with the capture of track and trace barcode data could provide additional insights.

Monitoring Visual Integrity Across a Global Production Network

CMOs are increasingly a part of production and the manufacturing process has been miniaturized to the extent it can now take place almost anywhere. But different facilities, operators, equipment, and excipients can produce output with significant variation in appearance. Deviation in visual appearance of a product can increase the potential for recalls as well as make it easier for counterfeiters to pass imitations as authentic. Undocumented variation also makes it more difficult to determine the source of diverted product. Authentication of each batch prior to release ensures the product is visually within statistical bounds of visual authenticity. If slight visual variation is desired, then new appearance models can be seamlessly added to increase the scope of the definition of authentic. One application of this is to create slight visual variation between lots to track parallel trade between markets. In this way the definition of authentic can keep pace with an increasingly complex manufacturing network.

Crisis Intervention, Management and Brand Protection

 It’s your worst nightmare. The legitimate supply chain has been breached and a counterfeit causes newsworthy harm to patients. Where to start and how to respond? Rapid deployment of an easy to use smartphone app that allows patients, pharmacists, public health, and law enforcement officials to quickly authenticate your medications projects a strong message of corporate responsibility and preparedness, and allows your compliance, regulatory, and crisis/brand management teams to stay ahead of potentially damaging media coverage. In addition, the extent of the breach and visual characteristics of the dangerous counterfeit can be quickly captured and shared with public health and law enforcement.

Patient Adherence and Logistical Data Converge

In addition to verifying integrity at the end of the supply chain, authentication can be incorporated into branded patient adherence monitoring tools, and accomplish two goals in one – knowledge that the patient received an authentic, unadulterated medication, and observing how they consume them. Along with location and timing information, the value of the data reaches beyond supply chain to marketing and clinical colleagues.

“I can authenticate those pills in one Snap, Jim.”

 New highly scalable authentication technology will broaden interest in product security as a marketing opportunity in emerging markets, increase the ability of QA to track visual variation in product across manufacturing sites, shut down easy routes for counterfeiter profit, and provide new data sets for use by our clinical and marketing colleagues.

Email this to someoneShare on Google+Share on LinkedInTweet about this on TwitterShare on Facebook