Risk Prediction Tool for Assessing the Probability of Death or Myocardial Infarction in Patients With Stable Coronary Artery Disease.

Several risk scores in acute coronary syndromes are available, but few models exist for stable coronary artery disease to guide decision-making and prognosis. A multivariate model was developed using 23 baseline candidate variables from the Clinical Outcomes Utilizing Revascularization and Aggressive Drug Therapy EvaluationTrial (n = 2,287 patients). Discrimination of the model was evaluated by the concordance c-index. The procedure was validated using 100 random half samples. We identified 9 independent predictors of death or myocardial infarction (MI) during a 5-year follow-up. The following predictors and points contributing to the risk score were: heart failure (3), number of diseased coronary arteries (1 for each vessel), diabetes (1), age (1 for each 15 years ≥ age 45), previous revascularization (1), current smoking (1), female (1), previous MI (1), and high-density lipoprotein cholesterol (1: 31 to 40 mg/dL; 2: <30 mg/dL). The risk tool had a potential range from 0 to 15, corresponding to 5-year event rates of 5.8% to 56%. C-indices ranged from 0.67 for the full data set to 0.62 for the validating subsamples. Respective observed versus predicted 5-year event rates for 3 predefined risk strata revealed: 30% had a low-risk score of 0 to 3 (9.3% vs 9.3%, or 1.9%/year); 59% had an intermediate-risk score of 4-6 (18.0% vs 18.1%, or 3.6%/year); and 11% had a high-risk score of 7-11 (36% vs 36.5%, or 7.2%/year). This stable coronary artery disease risk score permitted a prognostic assessment of 5-year probability of death or MI with an approximate 4-fold range in event rates from the lowest (9.3%) to the highest (36%) terciles, thus enabling better clinical practice decisions that allow physicians to tailor the intensity of treatment to the level of risk.

P values: from suggestion to superstition.

A threshold probability value of 'p≤0.05' is commonly used in clinical investigations to indicate statistical significance. To allow clinicians to better understand evidence generated by research studies, this review defines the p value, summarizes the historical origins of the p value approach to hypothesis testing, describes various applications of p≤0.05 in the context of clinical research and discusses the emergence of p≤5×10(-8) and other values as thresholds for genomic statistical analyses. Corresponding issues include a conceptual approach of evaluating whether data do not conform to a null hypothesis (ie, no exposure-outcome association). Importantly, and in the historical context of when p≤0.05 was first proposed, the 1-in-20 chance of a false-positive inference (ie, falsely concluding the existence of an exposure-outcome association) was offered only as a suggestion. In current usage, however, p≤0.05 is often misunderstood as a rigid threshold, sometimes with a misguided 'win' (p≤0.05) or 'lose' (p>0.05) approach. Also, in contemporary genomic studies, a threshold of p≤10(-8) has been endorsed as a boundary for statistical significance when analyzing numerous genetic comparisons for each participant. A value of p≤0.05, or other thresholds, should not be employed reflexively to determine whether a clinical research investigation is trustworthy from a scientific perspective. Rather, and in parallel with conceptual issues of validity and generalizability, quantitative results should be interpreted using a combined assessment of strength of association, p values, CIs, and sample size.