Using Google To Help Predict Side Effects of Mixing Drugs

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."

Comments

And the new troll game is

[maroberts]

...seeding Google with false comments on drugs to produce something similar to the Santorum effect.

Better than chance

[BSAtHome]

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?

Re:Better than chance

[ranulf]

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 to detect.

Re:Better than chance

[Anonymous Coward]

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

Re:Better than chance

[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.

Re:Better than chance

[Twinbee]

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:Better than chance

[jkflying]

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

Re:Better than chance

[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 different reactions, none of my numerous doctors can predict what interactions and side effects I might experience. They usually just tell me to ramp up on a new med slowly, ramp down on old meds slowly, and call them if anything strange happens. Even with that degree of caution, I've ended up in an ER with dangerous (and terrifying) interaction effects. And in those situations my doctors have always expressed indifferent "oh well, guess we need to try something else" attitudes.

So for me Google has been quite valuable in researching potential side effects and interactions that have been experienced by real people with similar medical profiles. Based on this research I've refused some drugs docs have suggested, and suggested some drugs all my docs have overlooked. Since taking the driver's seat with my own regimen based on internet research I've been MUCH better than I was when I just accepted the words of the "experts".

The 81%/19% statistic mentioned above doesn't mean you will have a 19% chance of dying if you take Dr. Google's advice. I see this as a potentially useful tool that streamlines one particular use that lots of people like me are already using Google for. Combined with a doctor's experience and (most importantly) my own knowledge and experiences, it might be quite valuable.

Hyper- not Hypoglycemia

[mystikkman]

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.

article says they used microsoft

[alen]

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

Hmmm....

[QilessQi]

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

About 7,950,000 results (0.33 seconds)

Seems legit.

No joke

[NormAtHome]

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:No joke

[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 she needs, not getting fat).