Viewpoint: pancakes and medical statistics.

Everyone is willing to expend considerable effort seeking authenticity; for example, the author sometimes travels over 100 miles to eat authentic and delicious homemade pancakes in a small-town restaurant. In the same way, physicians seek authenticity of care, which is another way of saying they seek the truest knowledge available when treating their patients. Because there are so many possible causes of many patients' complaints, physicians invoke the statistical theory behind the chief complaint (e.g., Which test for the complaint has the highest value?). In a world where medicine must be practiced with attention to resources and cost and where the answer must be reached in the fewest steps, evidence-based medicine (EBM) has risen to prominence. But how do clinicians ensure that the EBM literature is giving them the truest available knowledge? The author observes that clinicians and others have trusted the peer-review system to safeguard them against errors in the clinical literature. But he contends that errors are getting through at an increasing rate, and that physicians cannot automatically trust the peer-review process. Instead, they must become judges of experimental design, statistics, and analysis and assume the responsibilities that they had hoped the peer-review system would bear for them. He speculates about the reasons that peer review is no longer sufficiently ensuring authenticity in the literature. And to alleviate this problem, he recommends that current approaches to educating physicians about experimental design and statistics be augmented by making a beginning knowledge of statistics a requirement for entry into medical school.