Evidence-based medicine should be practiced for primary prevention and secondary prevention of cardiovascular disease. Randomized clinical trials have demonstrated, on numerous occasions, no difference or a worsening of clinical cardiovascular outcomes, whereas observational studies or studies relying on surrogate end points have shown a significant reduction in cardiovascular events by a therapeutic intervention. This editorial will discuss a few of these studies.Numerous studies have demonstrated that patients with complex ventricular arrhythmias associated with heart disease are at increased risk for new coronary events and for sudden cardiac death. 1 Antiarrhythmic drugs were used in widespread practice to suppress ventricular arrhythmias to prevent sudden cardiac death prior to CAST I (Cardiac Arrhythmia Suppression Trial I). 2 In fact, recruitment for this study was slowed because physicians were reluctant to allow their patients to be randomized because of a 50% chance of their patients being randomized to placebo.CAST I was a prospective, double-blind, randomized study in survivors of myocardial infarction with asymptomatic or mildly symptomatic ventricular arrhythmias, in which 730 patients were randomized to encainide or flecainide and 725 patients to placebo. 2 Adequate suppression of ventricular arrhythmias by encainide or flecainide was required before randomization. Despite adequate suppression of ventricular arrhythmias by encainide or flecainide, at 10-month followup encainide and flecainide significantly increased mortality from arrhythmia or cardiac arrest (relative risk [RR]: 3.5, 95% confidence interval [CI]: 1.7-8.5) and significantly increased all-cause mortality (RR: 2.5; 95% CI: 1.6-4.5). 2 Numerous studies have demonstrated that a low serum high-density lipoprotein (HDL) cholesterol is a risk factor for coronary artery disease (CAD). 3,4 We showed by multivariate analysis at 40-month follow-up of 664 older men and at 48-month follow-up of 1488 older women that there was a 1.70 times higher probability of developing new coronary events in men and a 1.95 times higher probability of developing new coronary events in women for a decrement of 10 mg/dL of serum HDL cholesterol. 4 However, does increasing serum HDL cholesterol by drug therapy reduce cardiovascular events? In aThe author has no funding, financial relationships, or conflicts of interest to disclose. randomized double-blind study of 15 067 patients at high cardiovascular risk, patients were randomized to torcetrapib plus atorvastatin or atorvastatin. 5 At 12-month follow-up, patients treated with torcetrapib had a 72% increase in serum HDL cholesterol. However, patients treated with torcetrapib had a 25% increase in cardiovascular events (P = 0.001) and a 58% increase in all-cause mortality (P = 0.006). 5 Compared with simvastatin plus placebo, the combination of fenofibrate plus simvastatin did not reduce the incidence of fatal cardiovascular events, nonfatal myocardial infarction, or nonfatal stroke at 4.7-year follow-up in 5518...