Performance of the Net Reclassification Improvement for Non-nested Models and a Novel Percentile-based Alternative.

In this study, we evaluated the performance of the NRI in a non-nested context by using it to compare competing cardiovascular risk prediction models. We explored the NRI's sensitivity to variations in risk categories and to the calibration of the compared models. We found that the NRI was very sensitive to changes in the definition of risk categories, especially when at least one model was mis-calibrated. To address these shortcomings, we describe a novel alternative to the usual NRI that uses percentiles of risk instead of cut-offs based on absolute risk. This percentile-based NRI demonstrates the relative ability of two models to rank patient risk. It displays more stable behavior, and we recommend its use when there are no established risk categories or when models are mis-calibrated. PMID: 29304237 [PubMed - as supplied by publisher]
Source: Am J Epidemiol - Category: Epidemiology Authors: Tags: Am J Epidemiol Source Type: research