A SAS macro for constrained randomization of group-randomized designs.

Group-randomized study designs are useful when individually-randomized designs either are not possible, or will not be able to estimate the parameters of interest. Group-randomized trials often have small number of experimental units or groups and strong geographically-induced between-unit correlation, thereby increasing the chance of obtaining a "bad" randomization outcome. It has been suggested to highly constrain the design through restriction to those allocations that meet specified criteria based on certain covariates available at the baseline. We describe a SAS macro that allocates treatment conditions in a two-arm stratified group-randomized design that ensures balance on relevant covariates. The application of the macro is illustrated using two examples of group-randomized designs.

Treatment of a clinically determined lower-risk stage III non-lymphoblastic Non-Hodgkin lymphoma with less intensive therapy does not impact negatively on outcome.

Stage III NHL was divided into lower-risk (LR) or high-risk (HR) groups. Results of treatment were retrospectively reviewed for patients between 1993 through 2000. An intensive multiagent protocol was used for IIIHR, and a CHOP-based, milder treatment for IIILR. Most LR therapy was outpatient, while treatment for HR patients was primarily inpatient. Five year EFS and OS for HR (n = 29) and LR (n = 23) groups was 86.2% and 95.6% (P = 0.26), and 93.1% and 100%, respectively (P = 0.4). LR had less toxicity. While these results need prospective confirmation, the data shows that less intensive therapy of a LR group of stage III NHL may not impact negatively on outcome.

Analysis of limb alignment in the pathogenesis of osteoarthritis: a comparison of Saudi Arabian and Canadian cases.

A study was made of alignment abnormalities and bone deformities in Saudis with osteoarthritis (SOA). Data from standardized radiography of hips and knees were: hip-knee-ankle angle (HKA), condylar-hip angle (CH), tibial plateau-ankle angle (PA), and joint surface (condylar-plateau) angle (CP). Females dominated the <50 years SOA subgroup (1.8:1), having also early onset OA with severe bowlegged deformity (mean HKA -11 degrees) and major shifts in CH, PA, and CP relative to normal parameters. In the females, links were noted between severe disease and osteomalacia or osteoporosis, requiring prospective studies. An association between femoral deformity (CH) and OA, first reported in Canadians with OA (COA), was confirmed in SOA (especially in males of all ages). The condition implies heightened mechanical risk of onset or progression at medial joint surfaces. Further, it calls for the fresh appraisal of surgical options based on biomechanical analysis of each case, including femoral osteotomy where necessary.