Newt Gingrich, John Kerry, and someone named Billy Beane (I have no clue who he is) argue that medicine is not yet sufficiently data driven.:

In the past decade, baseball has experienced a data-driven information revolution. Numbers-crunchers now routinely use statistics to put better teams on the field for less money. Our overpriced, underperforming health care system needs a similar revolution...

Remarkably, a doctor today can get more data on the starting third baseman on his fantasy baseball team than on the effectiveness of life-and-death medical procedures. Studies have shown that most health care is not based on clinical studies of what works best and what does not — be it a test, treatment, drug or technology. Instead, most care is based on informed opinion, personal observation or tradition.

Very true. Their call for evidence-based, data-driven medicine should be heeded, but you should know that the medical community has been on this for years now. It doesn't mean that the problem is solved, but today's medical students are being intensively educated in evidence-based medicine, and at the leading academic medical centers this is the way medicine is frequently practiced. Today's medical students are told that being a good physician includes knowing how to find and evaluate data, including increasingly common large-scale data sets that have to be evaluated using statistical models.

The change in the medical community isn't going to happen overnight, but the educational element has been a major priority at medical schools for years now. The current generation of physicians coming out of medical schools will eventually make evidence-based medicine standard practice.

Yet there is a chance of going too far towards number-crunching. Some authors have suggested that a physician's judgment can largely be replaced by computer models, just as baseball talent scouts are put to shame by someone with piles of stats and a computer. In many fields, from finance to wine evaluation to baseball, going by the numbers looks like the "new way to be smart." But human biology is a lot messier than baseball, and accurate prediction involves more numbers than we currently have available. The error margins of models we could make today would be unacceptably high. Right now, the best solution is producing physicians who are comfortable with both data and professional judgment.

To their credit, Beane, Gingrich and Kerry emphasize this point:

Evidence-based health care would not strip doctors of their decision-making authority nor replace their expertise. Instead, data and evidence should complement a lifetime of experience, so that doctors can deliver the best quality care at the lowest possible cost.

It goes without saying that to practice evidence-based medicine, you need evidence. This evidence comes from three major efforts: basic research, to understand the biology behind disease; translational medicine, which converts basic research into clinical practice; and clinical research, an effort to continuously evaluate, over the long-term, every aspect of how we practice medicine.

In order to do this effectively, we really ought to reorganize how the National Institutes of Health funds research. Right now, the NIH is divided up into disease-based institutes, but so much of today's research cuts across many institute boundaries. The NIH should reorganize with a center focused on basic research, one focused on translational medicine, a drug trials institute, and one along the lines of that proposed by Beane, Gingrich and Kerry - an institute that sponsored both sponsors clinical research and makes available in one place best-practices guidelines for busy physicians.

The most important point is this: while we're all hoping that new science will find new disease cures, we can already make big improvements in our health care by making rational decisions grounded in knowledge that is already available.