Pattern-Recognition + Social Networking = Drug Research in the Trenches

Photo: Proto Magazine

The marvelously well-researched and always provocative medical news magazine Proto, for which I occasionally write, has an intriguing story in this fall’s issue. Called “Between the Lines,” it’s a piece about how the online patient community Inspire.com is among a few such medically-oriented social networking sites that is beginning to use sophisticated natural language processing techniques borrowed from computer science to mine posts for clinically relevant information linking particular medications with symptoms and side-effects. Here’s a snippet from the article:

A query for mentions of the multiple sclerosis drug Avonex, for example, would parse a post by one user who writes, “i felt worse on avonex than my ms made me feel. while on avonex my psoriasis got VERY VERY bad/worse.” Another post reads, “I have been losing my hair…. I am going to switch from AVONEX to COPAXONE…to see if it is the AVONEX that is causing my hair issues.” After the program sorts through the text, Simetric employees review the results, double-checking the computer’s interpretations and dealing with tricky cases. The software may, for example, have trouble with the apparent contradiction of “wicked good” or pass over phrases it hasn’t been programmed to recognize.

The technique is a terrific mash-up of the emerging powers of the social networking phenomenon with the emerging powers of natural language processing, and it’s a really beautiful illustration of what’s possible when you find ways to analyze and quantify information that people naturally want to share with each other. I love it.