Follow Slashdot blog updates by subscribing to our blog RSS feed


Forgot your password?
AI Google Medicine Science

Using Google To Help Predict Side Effects of Mixing Drugs 47

sciencehabit writes "Pharmaceuticals often have side effects that go unnoticed until they're already available to the public. Doctors and even the FDA have a hard time predicting what drug combinations will lead to serious problems. But thanks to people scouring the web for the side effects of the drugs they're taking, researchers have now shown that Google and other search engines can be mined for dangerous drug combinations. In a new study, scientists tried the approach out on predicting hypoglycemia, or low blood sugar. They found that the data-mining procedure correctly predicted whether a drug combo did or did not cause hypoglycemia about 81% of the time."
This discussion has been archived. No new comments can be posted.

Using Google To Help Predict Side Effects of Mixing Drugs

Comments Filter:
  • ...seeding Google with false comments on drugs to produce something similar to the Santorum effect.

  • Better than chance (Score:3, Insightful)

    by BSAtHome ( 455370 ) on Thursday March 07, 2013 @09:11AM (#43103395)

    81% is better than a coin flip, but 19% chance of dying (or worse) using Google Doctor(TM) advice is maybe not as good as a Real Doctor(TM).

    Maybe they should try BigPharma(TM) commercials instead and find a reverse-cross-correlation?

    • by ranulf ( 182665 )

      Also, people don't google when they are taking drugs and not suffering side effects, people google multiple times with different queries when they do &c, so there's little in the way of accuracy in the numbers of people affected in each case.

      The only sensible way to interpret the numbers provided is "for the symptoms found b y this approach for a given drug, there's a 20% chance the symptom isn't in fact caused by this drug at all." Which makes it pretty useless for determining symtpoms that are hard

    • I hope this ends better for the non-medically trained researcher(s) than looking up symptoms and positing which disease one's suffering from.
    • Re: (Score:2, Insightful)

      by Anonymous Coward

      whooosh, the doctors doesnt have a clue, thats why they are doing this

    • Re: (Score:2, Informative)

      by Anonymous Coward

      You are confusing the matter. The algorithm isn't prescribing medicine, it is just reviewing bad mixes. If a bad mix is found, then researchers can validate that and use that to train doctors and put warnings on medication.

    • by Twinbee ( 767046 ) on Thursday March 07, 2013 @09:34AM (#43103523) Homepage
      I'm sure for some rarer drug combinations, 81% is a lot better than most real doctors could hope for. They're not infallible.
      • Re: (Score:2, Interesting)

        by Anonymous Coward

        Doctors are not even close to infallible. I suffered a severe injury (SCI) six years ago and as a result I'm quite acquainted with lots of doctors and lots of prescription drugs. I'm currently taking eight different meds daily, some delivered via intrathecal pump directly into my CSF. (This is after several attempts to prune down my list of medications and dosages as much as possible.)

        With that many (mostly somewhat unusual) meds floating around in my system, and the fact that each person might experience d

    • by jkflying ( 2190798 ) on Thursday March 07, 2013 @10:01AM (#43103731)

      The question is whether this 81% is better than Real Doctor. The assumption that Real Doctor gets everything right is, from personal experience, wrong.

    • Maybe they should try BigPharma(TM) commercials instead and find a reverse-cross-correlation?

      Presumably if they did that, it would tell you never to prescribe anything to anyone for anything.

      Hmm, I find your ideas intriguing...

  • It was hyperglycemia, not hypoglycemia, the exact opposite. Also, the research was helped by Microsoft, while Google is plastered all over the summary with nary a mention of Microsoft.

  • by alen ( 225700 ) on Thursday March 07, 2013 @09:36AM (#43103539)

    specifically data from IE about search queries to all the search engines

  • by Anonymous Coward

    If correlated correctly, the entire sum of human knowledge on the internet is more likely to come up with a correct answer than an average doctor using the database within their brain. Gee, who would have thought it?

    Of course the correct methodology would be to have doctors doing the Googling. I would hope that professional pride would not prevent physicians from using an established "expert system" to improve the outcomes for their patients.

    • "If correlated correctly", yes, but correlation is a difficult one for these kinds of searches.
      Not every doctor can simply do this. The results of the search were used as a guide which drug interaction to test. There are thousands of drugs. That's a lot of possible interactions.
      An example: Assume there are 10,000 different drugs (I have no clue how many there actually are). To test all of the possible interactions all these drugs you need 100,000,000 tests and these tests are expensive.

      For this stud
  • by QilessQi ( 2044624 ) on Thursday March 07, 2013 @09:43AM (#43103575)

    (Googles "microsoft windows, caffeine, death". )

    About 7,950,000 results (0.33 seconds)

    Seems legit.

  • No joke (Score:5, Insightful)

    by NormAtHome ( 99305 ) on Thursday March 07, 2013 @10:04AM (#43103761)

    I don't know how many people here have elderly parents but my mother is on over ten prescription medications and I've strongly suspected for years that some issues she's having are undocumented drug interactions. I've talked to several of her doctors and the best that they can come up with is "Sorry, there's no real data to support that theory / claim; nothing I can do".

    There really needs to be a system in place to gather data on people who are on this level of medication and try and figure out if some of their problems that started after they were on combinations of medication are related.

    • Re: (Score:2, Insightful)

      by Anonymous Coward

      So my grandmother was in declining health (~90) recently and everyone we talked to Doctor wise had nothing helpful to contribute until one doctor stepped in and finally said, "If you put her in hospice they will completely reevaluate her meds and odds are she'll get better." No doc was willing to take her off of anything outside of hospice because of liability concerns if she got worse / died. We put her in hospice, they pulled back a bunch of meds and now she's alert and regaining lost weight (weight that

    • There really needs to be a system in place to gather data on people who are on this level of medication

      It'd be too Big Brotherish for too many people - especially the older generations that need that data gathering the most.

      • I realize that would concern a lot of people and HIPA regulations may come into play but there are a lot of elderly people having a lot of problems because they're on a "cocktail" of more than six medications and many are having undocumented drug interactions. There has to be a way to gather anonymous statistics that doctors and pharmacists can use to better say to patients "Doctor B is prescribing ABCXYZ and that may cause you problems because you're already taking DEFXYZ and GHIXYZ medications and adding

    • by toebob ( 1996944 )
      I used to work for a pharma supporting a system that does exactly this. All pharmas have a system like this mandated by law. It's called adverse event tracking. You tell your doctor "I had effect D while taking drugs X, Y, and Z". The doctor reports this to the pharmas that make X, Y, and Z and it is all tracked for potential causality. The difficulties arise if there are too few people who have that side effect while taking that combination of medicine. If the occurrence is too rare there isn't enoug
  • The only way stuff could be on google, is if said stuff already happened. ie: People having already suffered the consequences of dangerous drug interactions.

    While it's certainly useful to have this knowledge, I fail to see how this translates to 'predicting' drug interaction. If people are googling for a combination of drug + a specific side effect, then they either are trying to find out if such an effect exists, or they have reason to suspect that such an effect exists, which *somebody* likely (and ina

  • Presumably the idea is that people experiencing reactions to drug combinations will go in the web and look for advice. And in so doing, we can use Google to pick up on this chatter and therefore determine adverse effects. So, the drugs are already on market and out there being consumed. Surely it would be far better to just have good old fashioned surveillance through clinic staff... less noise, etc. i don't see the advantage of using Google to reveal interactions in drugs that are already out there.

  • This research (AFAICT from readying the original article, but not the scientific papers behind it) is not about prediction at all, it is about discovery. Google and Bing are not "A Logic Named Joe," about to infer subtle connections between different medical research papers and predict troubles when two drugs are combined. They just uncover when people are searching on (and thus, potentially having) multiple sets of symptoms. The difference is rather crucial - if two drugs have lethal side effects when com

  • The sad, pathetic fact is you need to mine the data to find relevant information. Humans themselves don't have the time or patience to do this type of research manually, and it's an unrealistic burden that we should all be equipped with data mining and analytical tools just so we can use google's otherwise useless map of the web to find out, for example, whether prednisone can cause intense suicidal ideation when given in combination with fluoxetine. (Which is semi-standard FDA packaging warning for prednis

  • IUTBAP (I used to be a pharmacist).

    One of the things we studied were drug interactions.

    Basically pharmacists are more qualified to know these interactions, because they studied pharmacology, as well as pharmaceutics (how drugs are presented, what each form's method of spreading to the affected area(s) are, ...etc.)

    The clinical pharmacy movement was started back several decades ago, so doctors would diagnose, then pharmacists would prescribe together with the doctors, taking into account many things, like ot

  • Impairs your navigational ability because you're always pointing North.

"How many teamsters does it take to screw in a light bulb?" "FIFTEEN!! YOU GOT A PROBLEM WITH THAT?"