SAS Macro for Multiple Simple Logistic Regression Analyses with Application to Predictors of New Onset Diabetes After Renal Transplant (NODAT)

• Activity Number: 533
• Type: Contributed
• Date/Time: Wednesday, August 4, 2010 : 10:30 AM to 12:20 PM
• Sponsor: Section for Statistical Programmers and Analysts
• Author(s): Brie N. Noble*+ and Amylou C. Dueck and Joseph G. Hentz and Qing Wu and Harini A. Chakkera
• Companies: Mayo Clinic and Mayo Clinic and Mayo Clinic and Mayo Clinic and Mayo Clinic
• Keywords: SAS ; macro ; renal transplant ; logistic regression ; new onset diabetes

Abstract

New onset diabetes after renal transplant (NODAT) has adverse effects on both patient and graft survival. A first step to identifying pre-transplant measures which predict NODAT is simple logistic regression analyses using multiple predictor variables. We developed a SAS macro to summarize multiple simple logistic regression analyses in a concise table including odds ratios, confidence intervals, and p-values. Special features include options for AMA standardized p-values and unit specification for meaningful odds ratio interpretation of continuous predictors. Macro features are demonstrated via application to a cohort of 377 patients undergoing renal transplant. We identified that pre-transplant age, BMI, fasting glucose, steroid use, and the use of gout medication were statistically significant (P< 0.05) simple predictors of NODAT 1 year post renal transplant. SAS code will be provided.