Fact: Every medication prescribed by your doctor has been studied, tested and approved by the FDA. This should make you feel comfortable about what you’re putting in your body. But what you may not know and that is a little bit harder to study is what side effects you are opening yourself up too when you mix medication.

Dr. Russ Altman
Russ Altman

In his TEDMED talk, data scientist Russ Altman explains how doctors are beginning to study mixing drug interactions with a surprising too— search engine queries.

According to Altman, prior to this very new big data solution, the industry relied purely on “post marketing surveillance” to understand the implications of mixed medications. But now, the idea is that patients can use online “interaction checkers” to find the potential side effects of mixed medications.

The interaction checker for WebMD doesn’t claim perfection. It has a pretty clear disclaimer:

“This tool may not cover all possible drug interactions… Although we attempt to provide accurate and up-to-date information, no guarantee is made to that effect.”

Altman decided that this wasn’t enough so he challenged one of his students to use even more data to find more substantial answers about what happens when we mix drugs.

“The only hope — only hope — to understand these interactions is to leverage lots of different sources of data in order to figure out when drugs can be used together safely and when it’s not so safe.” said Altman.

Altman explained that they began with a public list from the FDA that included “hundreds of thousands of adverse event reports from patients, doctors, companies, pharmacists.”

From these reports they found out that patients who were on antidepressants and high cholesterol medications experienced a bump in glucose – a bump big enough for people to start worrying about developing diabetes.

They found this in ten patients though, which wasn’t enough to convince anyone. They then partnered with Vanderbilt and Harvard only to find similar similar results among their patient databases. Once they had proof that these medications were leading to even more side effects, they decided to increase the data pool even more.

They started using search engine queries. That means they found every time someone typed something like “peeing more than normal” into internet explorer. From this they were able to define how one drug interacted with one another based on what was being searched and they were able to find a bigger pool of answers.

“We published this, and it got some attention. The reason it deserves attention is that patients are telling us their side effects indirectly through their searches,” Altman continued. “We brought this to the attention of the FDA. They were interested. They have set up social media surveillance programs to collaborate with Microsoft, which had a nice infrastructure for doing this, and … to look at Twitter feeds, Facebook feeds, search logs, to try to see early signs that drugs, either individually or together, are causing problems.”

Altman’s point being that big data can have the potential to solve this problem for people who are not only on one or two, but three, four or five medications.

Here’s to hoping that this solution creates a future where doctors and patients have a better understanding of the complexities of prescription medications.

Watch the talk below: