HighlightsThe %pshreg SAS macro fits Fine-Gray models for competing risks.The macro first modifies a given data set and then uses PROC PHREG for analysis.Many useful features of PROC PHREG can now be applied to a Fine-Gray model.Time-dependent effects can be accommodated by time-by-covariate interactions.For small data sets, the Firth correction is available.

Statistical models are simple mathematical rules derived from empirical data describing the association between an outcome and several explanatory variables. In a typical modeling situation statistical analysis often involves a large number of potential explanatory variables and frequently only partial subject-matter knowledge is available. Therefore, selecting the most suitable variables for a model in an objective and practical manner is usually a non-trivial task. We briefly revisit the purposeful variable selection procedure suggested by Hosmer and Lemeshow which combines significance and change-in-estimate criteria for variable selection and critically discuss the change-in-estimate criterion. We show that using a significance-based threshold for the change-in-estimate criterion reduces to a simple significance-based selection of variables, as if the change-in-estimate criterion is not considered at all. Various extensions to the purposeful variable selection procedure are suggested. We propose to use backward elimination augmented with a standardized change-in-estimate criterion on the quantity of interest usually reported and interpreted in a model for variable selection. Augmented backward elimination has been implemented in a SAS macro for linear, logistic and Cox proportional hazards regression. The algorithm and its implementation were evaluated by means of a simulation study. Augmented backward elimination tends to select larger models than backward elimination and approximates the unselected model up to negligible differences in point estimates of the regression coefficients. On average, regression coefficients obtained after applying augmented backward elimination were less biased relative to the coefficients of correctly specified models than after backward elimination. In summary, we propose augmented backward elimination as a reproducible variable selection algorithm that gives the analyst more flexibility in adopting model selection to a specific statistical modeling situation.

Increased sclerostin serum levels in CKD patients are not due to decreased renal elimination. On the contrary, renal elimination increases with declining kidney function. Whether this has consequences on antisclerostin antibody dosing, efficacy, or safety in patients with CKD remains to be determined.

Background Recent studies show associations between inorganic phosphate and risk of heart failure in the general population as well as between fibroblast growth factor 23 (FGF-23) and outcome in coronary heart disease. This study was carried out to assess whether circulating levels of inorganic phosphate and FGF-23, a new central hormone in mineral bone metabolism, predict outcome in systolic heart failure.

AimsPrevious risk assessment scores for patients with coronary artery disease (CAD) have focused on primary prevention and patients with acute coronary syndrome. However, especially in stable CAD patients improved long-term risk prediction is crucial to efficiently apply measures of secondary prevention. We aimed to create a clinically applicable mortality prediction score for stable CAD patients based on routinely determined laboratory biomarkers and clinical determinants of secondary prevention. Methods and resultsWe prospectively included 547 patients with stable CAD and a median follow-up of 11.3 years. Independent risk factors were selected using bootstrapping based on Cox regression analysis. Age, left ventricular function, serum cholinesterase, creatinine, heart rate, and HbA1c were selected as significant mortality predictors for the final multivariable model. The Vienna and Ludwigshafen Coronary Artery Disease (VILCAD) risk score based on the aforementioned variables demonstrated an excellent discriminatory power for 10-year survival with a C-statistic of 0.77 (P , 0.001), which was significantly better than an established risk score based on conventional cardiovascular risk factors (C-statistic ¼ 0.61, P , 0.001). Net reclassification confirmed a significant improvement in individual risk prediction by 34.8% (95% confidence interval: 21.7-48.0%) compared with the conventional risk score (P , 0.001). External validation of the risk score in 1275 participants of the Ludwigshafen Risk and Cardiovascular Health study (median follow-up of 9.8 years) achieved similar results (C-statistic ¼ 0.73, P , 0.001). ConclusionThe VILCAD score based on a routinely available set of risk factors, measures of cardiac function, and comorbidities outperforms established risk prediction algorithms and might improve the identification of high-risk patients for a more intensive treatment.--