Statistical Challenges in Development of Prognostic Models in Diffuse Large B-Cell Lymphoma: Comparison Between Existing Models - A Systematic Review

Background and Aim: Based on advances in the diagnosis, classification, and management of diffuse large B-cell lymphoma (DLBCL), a number of new prognostic models have been proposed. The aim of this study was to review and compare different prognostic models of DLBCL based on the statistical methods used to evaluate the performance of each model, as well as to analyze the possible limitations of the methods. Methods and Results: A literature search identified 46 articles that proposed 55 different prognostic models for DLBCL by combining different clinical, laboratory, and other parameters of prognostic significance. In addition, six studies used nomograms, which avoid risk categorization, to create prognostic models. Only a minority of studies assessed discrimination and/or calibration to compare existing models built upon different statistical methods in the process of development of a new prognostic model. All models based on nomograms reported the c-index as a measure of discrimination. There was no uniform evaluation of the performance in other prognostic models. We compared these models of DLBCL by calculating differences and ratios of 3-year overall survival probabilities between the high- and the low-risk groups. We found that the highest and lowest ratio between low- and high-risk groups was 6 and 1.31, respectively, while the difference between these groups was 18.9% and 100%, respectively. However, these studies had limited duration of follow-up and the number of patients ranged from 71 to 335. Conclusion: There is no universal statistical instrument that could facilitate a comparison of prognostic models in DLBCL. However, when developing a prognostic model, it is recommended to report its discrimination and calibration in order to facilitate comparisons between different models. Furthermore, prognostic models based on nomograms are becoming more appealing owing to individualized disease-related risk estimations. However, they have not been validated yet in other study populations.