Denic A, et al. - Researchers performed this nested case-control study in kidney transplant recipients with a surveillance biopsy obtained 5 years after transplantation in order to test their hypothesis that graft loss could be more efficiently predicted via scoring histologic features of digitized renal allograft biopsies using a continuous, more objective, computer-assisted morphometric (CAM) system. They compared the risk of graft loss between CAM-based models vs a model based on Banff scores (not developed to predict graft loss). Compared to Banff models, CAM-based models predicted graft loss more efficiently using 5-year renal allograft surveillance biopsies.