predictNMB: An R package to estimate if or when a clinical prediction model is worthwhile
Rex Parsons, Robin D. Blythe, Adrian Gerard Barnett, Susanna M. Cramb, Steven McPhail · The Journal of Open Source Software · 2023
Clinical prediction models are frequently developed for identifying patients at risk of adverse health events, and possibly guiding the use of treatment, but are often not validated or implemented in clinical practice (Hendriksen et al., 2013;Steyerberg et al., 2013).This could be due to several factors including poor performance or the lack of an effective intervention that can be implemented in response to prediction of high risk.The predictNMB R package performs simulations to evaluate the use of hypothetical clinical prediction models (with a binary outcome) to help inform development and implementation decisions, and estimate potential impacts in terms of costs and health outcomes.This package allows the user the flexibility to adjust simulation inputs regarding the prediction model's performance, its target population, the costs of the event being predicted, and the effectiveness of interventions that the model is being used to recommend.More details about the package, including guides and a detailed example are available on the package site.