Researchers at the University of Virginia and West Virginia University are collaborating to create data-analysis tools, aimed at identifying early signs of adverse drug reactions on social media media sites.
Under a $130,000 grant from the National Science Foundation, University of Virginia Professor Ahmed Abbasi and his team are studying four types of social media (websites, blogs, Web forums and social-networking sites) for information on adverse reactions, according to a UVA Today article.
The FDA already relies on consumers to report side-effects through physicians and other reporting channels once drugs come to market. Abbasi said using social media to glean product safety feedback isn't a big leap.
However, there are challenges that come with the next generation of product feedback through social media--the ever existing "big data" challenge.
Researchers are looking at social media posts from 2000 to 2012, with an estimated 20 percent of medical information on the Web being spam, researchers noted.
Nevertheless, social media can be more reliable and timely than traditional sources of media, Abbasi said.
"[T]he idea is for the FDA and other key stakeholders to get the initial signals earlier, allowing them to investigate leads sooner and make the final pronouncements about adverse drug reactions."
Researchers have been leveraging early-detection technology. Drug reactions cause about 20 percent of drugs in clinical development to fail, FierceHealthIT previously reported. With dollars at stake, early detection could help mitigate those costs.
A study published last month in the journal Nature outlined a computer model by researchers from the University of California San Francisco that can predict which drug prospects are most likely to have adverse side effects. The model not only helped drug makers find potential interactions earlier in the process, but it also helped in repurposing medications to treat other conditions.
For more information:
- see the research announcement
Related Articles:
VA Innovation Initiative project aims for fewer adverse drug events
Computer model helps predict adverse drug effects
Stanford-created algorithm distinguishes medication side effects
New online databases help patients find adverse events