Understand and Advance Drug Safety with Text Analytics

July 21 2016

Drug safety is, of course, a prime focus of anyone in the pharmaceutical and biotech industries. The goal of any drug R&D project is to bring to market a safe and efficacious drug – oh yes, and ideally, create the latest blockbuster!

For monitoring drug safety, there are many tools and solutions. We were pleased to see the inclusion of Linguamatics I2E, in a recent paper from the FDA on the “Use of data mining at the Food and Drug Administration” (Duggirala et al, 2016, J Am Med Inform Assoc).

This FDA review covers a very broad range of text and data mining approaches, across both FDA databases (e.g. MAUDE, VAERS) and external data such as Medline, clinical study data, and social media.

Specifically, the FDA describe the use of I2E “to study clinical safety based on chemical structure information contained in medical literature. Linguamatics I2E enables custom searches using natural language processing to interpret unstructured text. The ability to predict the clinical safety of a drug based on chemical structures is becoming increasingly important, especially when adequate safety data are absent or equivocal.”

One powerful capability of I2E for drug safety is the ability to find, extract and standardize the key concepts (i.e. drugs, adverse effects) and also the context (e.g. dosage, population demographics, co-morbidities).  I2E integrates ChemAxon's JChem library to allow automatic recognition and extraction of chemical entities; for example, to search all of the FDA Drug Labels for adverse events associated with compounds similar to a particular drug or drug class.

In addition, mapping adverse events to MedDRA (Medical Dictionary for Regulatory Activities - an international medical terminology for diseases and adverse events), whether from drug labels, scientific literature, or even social media, enables the user to visualize and understand the adverse event landscape for the drugs of interest. And, if you are concerned about drug safety, rapid assessment and visualization of such profiles across a broad range of drugs and side effects is very valuable.


The heatmap below shows a normalized set of respiratory adverse events, extracted from FDA drug labels (DailyMed, available through I2E OnDemand) for a set of immunosuppressant drugs. FDA Drug labels are a fantastic source of drug-related information. With I2E, it’s possible to extract and differentiate adverse event profiles for marketed drugs and map these to MedDRA. The chart shows a snapshot of five immunosuppressant drugs with their profiles or “fingerprints” for one major adverse event class – respiratory side effects.  These charts from I2E demonstrate the power of visual analytics – you don’t need to know much about these drugs to see that their side effect profiles are different. 


Heatmap of immunosuppressant drugs with AEs