One of the most common requests that statisticians get from investigators are sample size calculations or sample size justifications. The sample size is the number of patients or other experimental units included in a study, and determining the sample size required to answer the research question is one of the first steps in designing a study. Although most statistical textbooks describe techniques for sample size calculation, it is often difficult for investigators to decide which method to use. There are many formulas available which can be applied for different types of data and study designs. However, all of these formulas should be used with caution since they are sensitive to errors, and small differences in selected parameters can lead to large differences in the sample size. In this paper, we discuss the basic principles of sample size calculations, the most common pitfalls and the reporting of these calculations.

Type 2 diabetes is associated with altered immune and hemostatic responses. We investigated the selective effects of hyperglycemia and hyperinsulinemia on innate immune, coagulation, and fibrinolytic responses during systemic inflammation. Twenty-four healthy humans were studied for 8 hours during clamp experiments in which either plasma glucose, insulin, both, or none was increased, depending on randomization. Target plasma concentrations were 5 versus 12 mM for glucose, and 100 versus 400 pmol/L for insulin. After 3 hours, 4 ng/kg Escherichia coli endotoxin was injected intravenously to induce a systemic inflammatory and procoagulant response. Endotoxin administration induced cytokine release, activation of neutrophils, endothelium and coagulation, and inhibition of fibrinolysis. Hyperglycemia reduced neutrophil degranulation (plasma elastase levels, P < .001) and exaggerated coagulation (plasma concentrations of thrombin-antithrombin complexes and soluble tissue factor, both P < .001). Hyperinsulinemia attenuated fibrinolytic activity due to elevated plasminogen activator-inhibitor-1 levels (P < .001). Endothelial cell activation markers and cytokine concentrations did not differ between clamps. We conclude that in humans with systemic inflammation induced by intravenous endotoxin administration hyperglycemia impairs neutrophil degranulation and potentiates coagulation, whereas hyperinsulinemia inhibits fibrinolysis. These data suggest that type 2 diabetes patients may be especially vulnerable to prothrombotic events during inflammatory states.

Background— Primary ventricular fibrillation (VF) accounts for the majority of deaths during the acute phase of myocardial infarction. Identification of patients at risk for primary VF remains very poor. Methods and Results— We performed a case-control study in patients with a first ST-elevation myocardial infarction (STEMI) to identify independent risk factors for primary VF. A total of 330 primary VF survivors (cases) and 372 controls were included; patients with earlier infarcts or signs of structural heart disease were excluded. Baseline characteristics, including age, gender, drug use, and ECG parameters registered well before the index infarction, as well as medical history, were not different. Infarct size and location, culprit coronary artery, and presence of multivessel disease were similar between groups. Analysis of ECGs performed at hospital admission for the index STEMI revealed that cumulative ST deviation was significantly higher among cases (OR per 10-mm ST deviation 1.59, 95% CI 1.25 to 2.02). Analysis of medical histories among parents and siblings showed that the prevalence of cardiovascular disease was similar between cases and controls (73.1% and 73.0%, respectively); however, familial sudden death occurred significantly more frequently among cases than controls (43.1% and 25.1%, respectively; OR 2.72, 95% CI 1.84 to 4.03). Conclusions— In a population of STEMI patients, the risk of primary VF is determined by cumulative ST deviation and family history of sudden death.