• Testing Medicines

    Testing Medicines

    We are developing low-cost tests that can be used outside of the lab to detect low-quality medications.

    Learn more

  • Undergraduate Research

    Undergraduate Research

    Undergraduates make important contributions to solving real-world problems.

    Learn more

  • Working Globally

    Working Globally

    International partnerships enable us to create practical solutions for the developing world.

    Learn more

A global problem

Many of the pharmaceuticals that are purchased in the developing world are substandard or outright fake drugs. Although there is no global system for monitoring the quality of medicine, study after study reveals pervasive poor quality and products that are worthless or even harmful to patients.  Many countries in the developing world do not have the technological infrastructure or regulatory resources to keep low quality medicines off the market shelves. And since the pharmaceutical trade is a lucrative global market, low quality medicine can cross borders and harm people anywhere in the world. 

New ways to find fake medicines

Paper analytical devices (PADs) are test cards that can quickly determine whether a drug tablet contains the correct medicines. They are cheap and easy to use. They don't require power, chemicals, solvents, or any expensive instruments, so they can be deployed rapidly at large scale if pharmaceutical quality is doubtful.

You can obtain PADs from our storefront, Paper Analytics LLC.  The PADreader app for Android phones is available free at the Google Play store.  




Root causes:

Negligence by manufacturers

  • A heart medicine called "Isotab" killed over 200 people in Pakistan when one batch was manufactured using toxic quantities of an antimalarial medicine in place of the inert filler that was supposed to be added.  According to the Pakistani government's report (pathology_of_negligence_pic_drug_inquiry_report_2012.pdf)  the antimalarial drug got wet during delivery, and was moved into a drum marked "starch".  No-one ever changed the label or noticed the substitution.  

Deliberate falsification by manufacturers or distributors

  • Fortune Magazine has a great investigatory report on Ranbaxy's contribution to this area.
  • Even secure supply chains fall victim;  see this WHO report on testing company Semler Research faking bioequivalence studies.  

Partnering with regulatory agencies

By sharing our results directly with medical regulatory agencies, we help them quickly discover poor quality medicines in their markets.  This enables them to negotiate with manufacturers and distributors from a position of knowledge and to take other regulatory and legal actions to protect patients from poor quality products.

Bringing market forces to bear

In the developing world, most buyers have to trust what the seller tells them about the quality of the pharmaceuticals they purchase. Unscrupulous manufacturers and distributors know that there is little chance that their medicines will be screened in a lab. These paper test cards don't need a lab, and they will enable people all over the world to quickly detect low quality medicines and remove them from the market.  


Congratulations to Olatunde Awosiji Awotunde, Nicholas Roseboom, and Jin Cai!

Author: Marya Lieberman

Discrimination of Substandard and Falsified Formulations from Genuine Pharmaceuticals Using NIR Spectra and Machine Learning

Near-infrared (NIR) spectroscopy is a low-cost analytical tool for rapid characterization of pharmaceuticals. Usually, it's necessary to build up a "library" of NIR spectra from authentic products in order to identify real and fake formulations.  In this paper, we developed a simple training method that uses binary mixtures of a pharmaceutical (acetaminophen) with two different cutting agents, and used several different data analysis models to extrapolate the training samples to real and fake samples of popular brands of acetaminophen tablets.   While none of the models was able to correctly classify all the samples, a simple voting algorithm was able to compensate for the weaknesses of the models and classify 93% of the samples correctly.  …

Read More