Clinical judgment and statistics. Lessons from a simulated randomized trial in coronary artery disease.

摘要: A simulated randomized clinical trial in coronary artery disease was conducted to illustrate the need for judgment and modern statistical methods assessing therapeutic claims studies of complex diseases. Clinicians should be aware problems that occur when a patient sample is subdivided treatment effects are assessed within multiple prognostic categories. In this example, 1073 consecutive, medically treated patients from Duke University data bank were into two groups. The groups reasonably comparable and, as expected, there no overall difference survival. subgroup 397 characterized by three-vessel an abnormal left ventricular contraction, however, survival group 1 significantly different 2 patients. Multivariable adjustment procedures revealed resulted combined effect small imbalances distribution several factors. Another identified which significant not explained multivariable methods. These unlikely examples trials disease. must exercise careful attributing such results efficacious therapy, they may due chance or inadequate baseline comparability