The NIH classification intends to standardize the diagnostic criteria for chronic CVHD and to establish prognosis groups that will help to identify patient risk and thus decide on the most appropriate treatment. This study assesses the predictive value of this classification and analyzes new prognostic factors in a series of 820 patients receiving allogeneic grafts at three sites: Hospital Universitario de Salamanca, Hospital de la Santa Creu i Sant Pau, in Barcelona, and Karolinska Institutet, in Stockholm. In the univariate analysis, the classification limited/extensive, the NIH class, and the type of onset have a significant influence on overall survival and transplant-related mortality. Additionally, the overlap syndrome is associated with a shorter survival in the multivariate analysis, only the NIH class-with on HR of 2.89 (95% Cl: 1.75-4.76; p < 0.007) for mild and moderate versus severe disease-has a significant influence on survival. Excluding the NIH class, the type of onset is Identified as an independent factor for survival. Therefore, the NIH class and the type of onset are confirmed as the most significant variables. This is important in order to identify patients with a higher risk of death after transplantation, and shorter survival. On the other hand, it is a very laborious classification; for this reason it is necessary to establish the degree of involvement of lungs, skin, digestive tract, and liver, and to identify the number of organs, because these factors significantly affect survival.