Data Mining Competition To Improve Drug Safety 36
An anonymous reader writes "The OMOP Cup is a competition to find new methods for detecting drug side effects. There have been several cases over the last few years where drugs have had issues that haven't been detected for years after they were released. The proliferation of electronic medical records and pharmacy claims provides a large and potentially powerful new data source for faster detection. The problem is that the techniques for doing this on a large scale are immature. The OMOP Cup is trying to help fix that. They've already given out $5,000 for top methods, and there's $15,000 still up for grabs."
Crap derived from crap? (Score:2, Interesting)
I'm curious as to what proportion of medical records were incorrect and what proportion of pharmacy claims were inaccurate. Just how useful could a database like this be, if its source data is prone to some really wacky error? Side effect misdiagnoses alone could make for a considerable slog through noise just to pick up an effect.
Data Mining Sing Along (Score:5, Funny)
You parse 16 gigs, and what do you get?...
Re:Data Mining Sing Along (Score:5, Funny)
A drug-induced tumor and deeper in debt.
Only $20K? (Score:2)
Not very much money when you consider the amount of money that gets paid out to plaintiffs in lawsuits filed over drug side effects, such as the ones concerning Vioxx. This whole thing sounds a lot like the pharmaceutical companies are looking for a cheap fix, an alternative to the extensive drug trials they ought to be doing.
Re: (Score:1)
Re: (Score:1, Insightful)
And then you *do* extensive drug trials, and people start complaining about how you torture animals, or how the price of the medicine is too high when it's finally on the market, or why they can't get the medicine while it's still in trial even though they don't fit the trial profile *at all* but it would save their kids life etc etc.
Re: (Score:2)
people start complaining about how you torture animals
Who cares.
how the price of the medicine is too high when it's finally on the market
Tough shit, save medicine is expensive, surprise!
why they can't get the medicine while it's still in trial even though they don't fit the trial profile *at all* but it would save their kids life etc etc.
I still dont understand why the FDA does not allow drugs that have not been certified to be administered to terminal patients. There is no additional risk from doing it.
Re: (Score:2)
If the government respected a citizen's right to determine what will and won't be put into their own body, we would have never had a War on Drugs. What you mention there is just a logical extension of the idea that none of us can be trusted with the slightest degree of self-determination, not even when it cannot impact the lives of others.
Re: (Score:3, Insightful)
Say goodbye to "quality of life" drugs. (Score:3, Insightful)
Dig through a huge dataset like this looking for problems and you will find them. For everything. And with the FDA and court's approach, that means that even tiny effects will end up getting drugs knocked off the market. The COX-2 inhibitors are a perfect example. Sure, for a tiny number of people taking them they increased the risk of heart attack. But for untold numbers of people taking them, they relieved pain either where nothing else would, or with far fewer side effects than other pain medications like opoids. But in today's society, we're not allowed to trade a tiny risk of death versus an enormous chance of pain relief. So even the very tiny risks one can find this way will end up getting whole classes of non-lifesaving drugs off the market. No more analgesics, no more antihistamines, no more decongestants (oh, wait, they already virtually banned those for the War on Drugs), no more cough medicines, etc.
ignorance != bliss (Score:3, Insightful)
Datamining by Kaiser Permanente helped find a previously unknown risk of heart attack for certain users of VIOXX [wikipedia.org], and it was probably right that the drug was withdrawn. It may also be a good idea to re-approve it for those who would benefit with minimal risk. But without the post-approval datamining we would never know what the risk/benefit truly was.
That also points to some limitations of our drug approval process. Trial patients are followed only for so long. In fact, some of the trial patients who we
Re: (Score:2)
It's not the science I object to; it's the politics. The Vioxx study, subsequent FDA action, and subsequent lawsuits resulted in nearly every COX-2 inhibitor being taken off and kept off the market, despite the tiny magnitude of the risks. Given that, I think it's better to not seek out knowledge of such small risks rather than risk that kind of overreaction.
in soviet russia (Score:1)
HIPAA anyone? (Score:2)
This strikes me as a huuuuuge breach of medical record confidentiality. Where exactly do they plan to legally get enough medical records to mine in the first place?
Re: (Score:2, Informative)
This strikes me as a huuuuuge breach of medical record confidentiality. Where exactly do they plan to legally get enough medical records to mine in the first place?
As long as eighteen HIPAA identifiers are removed, the data is considered deidentified by HIPAA. Deidentified data does not need patients' consent. De-identified data-only studies only need the hospital IRB (Institutional Review Board) approval. Believe me, it's not an easy task to get the IRB approval.
Here's the list of the 18 HIPAA identifiers [uvm.edu].
Re: (Score:2)
As long as eighteen HIPAA identifiers are removed, the data is considered deidentified by HIPAA. Deidentified data does not need patients' consent. De-identified data-only studies only need the hospital IRB (Institutional Review Board) approval. Believe me, it's not an easy task to get the IRB approval.
Here's the list of the 18 HIPAA identifiers [uvm.edu].
Even though it's a bit of a different situation, I'm reminded of the Netflix debacle [wired.com]..
Re: (Score:2)
How much for improving movie ratings? (Score:2, Insightful)
Re: (Score:2)
That's awesome, I can totally help out my fellow ... what's that? I get $1M if I rock NetFlix's movie rating DB? Movie ratings here I come!
You're a little late...the Netflix contest ended quite a few months ago, with the $1M being awarded to a joint AT&T Research/Yahoo Labs team.
Come again? (Score:2)
They've already given out $5,000 for top methods, and there's $15,000 still up for grabs.
Whoa there, big spender! I'm all for serving the public good, but if I was to work all those extra hours and discovered a useful new technique for using this data, and I have to choose between maybe getting somewhat less than what I still owe on my car, or trying to sell the code to the deep pockets of Big Pharma, I know which one I'm going to go with.
Re: (Score:2)
They've already given out $5,000 for top methods, and there's $15,000 still up for grabs.
Whoa there, big spender! I'm all for serving the public good, but if I was to work all those extra hours and discovered a useful new technique for using this data, and I have to choose between maybe getting somewhat less than what I still owe on my car, or trying to sell the code to the deep pockets of Big Pharma, I know which one I'm going to go with.
Can't disagree there, but I wanted to point out you probably want to sell this to class action attorneys for the real money. Pharmaceutical companies will bury this quicker than you can sign over the rights to it.
Wrong base assumptions. (Score:2)
The base assumption of this seems to be, that the point of a pharma company is to heal people with safe drugs.
It’s not. In fact, if they don’t lose money from it, it is completely irrelevant if you die a slow and horrible death.
Proven by many, many products that are out there right now. Like Prozac. It does help nobody. In fact it does the exact opposite, because it drives people even further into repression. And therefore dependency on the stuff.
The point of pharma companies, is to make money.
A
Re: (Score:2)
The base assumption of this seems to be, that the point of a pharma company is to heal people with safe drugs.
It’s not. In fact, if they don’t lose money from it, it is completely irrelevant if you die a slow and horrible death.
Proven by many, many products that are out there right now. Like Prozac. It does help nobody. In fact it does the exact opposite, because it drives people even further into repression. And therefore dependency on the stuff.
The point of pharma companies, is to make money.
As long as that is not 100% and without any loopholes, tied to what we want from them,
we will have no guarantee at all to get it.
You might want to consider some Prozac, you sound anxious.
I will lose money on this (Score:1)
Top Methods @ Top Bargain (Score:2)
Imagine, $20.000 that will help the poor Pharma-Industry to avoid being sued.
Alternatively:
Imagine, $20.000 that will save the health of numerous people.
Now, that is a big deal indeed.
CC.
Drug companies are evil (Score:1)