Slashdot Mirror
Fighting the Number-One Killer In the US With Data
mattydread23 writes "Often, the signs of eventual heart failure are there, but they consist of a lot of weak signals over a long period of time, and doctors are not trained to look for these patterns. IBM and a couple heathcare providers, Sutter Health and Geisinger Health System, just got a $2 million grant from NIH to figure out how better data analysis can help prevent heart attack. But the trick is that doctors will have to use electronic records — it also means a lot more tests. Andy Patrizio writes, 'What this means is doctors are going to have to expand the tests they do and the amount of data they keep. Otherwise, the data isn't so Big.'"
Utter rubbish. The French eat meat and have a high fat diet, but have a very low incidence of heart problems
Your link is to a fad-diet site.
It's also the perfect segue into Total Informational Awareness. It's basically data mining. You find a couple of soft indicators - the patient starts complaining of shortness of breath perhaps, has hypertension, is overweight. Then he moves. Starts over again. Doc asks the same question, patient puts down different dates (because they don't remember the doc visit five years ago), rinse lather repeat. If you could track this sort of stuff over time the 'computer' could start making some pretty easy correlations.
IF you had the data. And only IF you had the data. Which means linked EHRs. Which is an interesting concept and would likely help, except, given the current state of our Panopticon Plus government, you have to wonder exactly who they are trying to help.
Comrade.
Oh, AND IT'S HEART FAILURE NOT HEART ATTACK. THEY'RE DIFFERENT. If you're the editor at least glance at TFA. /pedant /normal blood pressure mode
Faster! Faster! Faster would be better!