aorsf: An R package for supervised learning using theoblique random survival forest
Byron C. Jaeger, Sawyer Welden, Kristin Lenoir, Nicholas M. Pajewski
Abstract
Risk prediction is a type of supervised learning where the goal is to predict the probability that a person will experience an event within a specific amount of time. This kind of prediction may be useful in clinical settings, where identifying patients who are at high risk for experiencing an adverse health outcome can help guide strategies for prevention and treatment. The oblique random survival forest (RSF) is a supervised learning technique that has obtained high prediction accuracy in general benchmarks for risk prediction However, computational overhead and a lack of tools for interpretation make it difficult to use the oblique RSF in applied settings.
Topics & Concepts
Random forestOblique caseR packageArtificial intelligenceStatisticsComputer scienceEnvironmental scienceMathematicsForestryGeographyLinguisticsPhilosophyStatistical Methods and InferenceMachine Learning and Data ClassificationBayesian Methods and Mixture Models