JMIR Publications

ABSTRACT

Background:

In drug development clinical trials, there is a need for balance between restricting variables by setting enrollment criteria and representing the more diverse patient population that may use a product once it is approved. Although recent policy initiatives focusing on inclusion of historically underrepresented groups are being implemented, barriers still remain. As a product, these clinical trial limitations may mask potential product benefits and side-effects. In an effort to bridge these gaps, online communication in health communities may serve as an additional population signal for drug side-effects.

Objective:

Employ a non-traditional data set to identify drug side-effect signals. Apply both Natural Language Processing (NLP) technology and hands-on linguistic analysis to a set of online posts from known statin users to 1) identify any underlying crossover between use of statins and impairment of memory or cognition and 2) to obtain patient lexicon in their descriptions of experiences with statin medications and memory changes.

Methods:

Researchers utilized User Generated Content (UGC) on Inspire.com, looking at over 11,000,000 posts across all of Inspire. Posts were written by patients and caregivers belonging to a variety of communities on Inspire. After identifying these posts, researchers used NLP and Hands-On Linguistic Analysis to draw and expand upon correlations between statin use, memory, and cognition.

Results:

NLP analysis of posts identified statistical correlations between statin users and discussion of memory impairment that were not seen in control groups. NLP found that out of all members on Inspire.com, 3.1% had posted about memory or cognition. In a control group of those who had posted about TNF Inhibitors, 6.2% had also posted about memory in cognition. In comparison, of all those who had posted about a statin medication, 22.6% also posted about memory and cognition. Further, Linguistic Analysis of a sample of posts provided themes and context to these statistical findings. In looking at posts from statin users about memory, four key themes are found and described in detail in the data: Memory Loss, Aphasia, Cognitive Impairment, and Emotional Change.

Conclusions:

Correlations from this study point to a need for further research on the impact of statins on memory and cognition. Further, using non-traditional data sets, such as online communities, NLP and Linguistic methodologies broadens the population for identifying side-effect signals. In side-effects such as memory and cognition, where self-reporting may be unreliable, this methodology can provide another avenue to inform patients, providers, and the FDA.