Perspectives on validation of clinical predictive algorithms
Anne de Hond, Vaibhavi Shah, Ilse Kant, Ben Van Calster, Ewout W. Steyerberg, Tina Hernandez‐Boussard
Abstract
The generalizability of predictive algorithms is of key relevance to application in clinical practice. We provide an overview of three types of generalizability, based on existing literature: temporal, geographical, and domain generalizability. These generalizability types are linked to their associated goals, methodology, and stakeholders.
Topics & Concepts
Generalizability theoryRelevance (law)Computer scienceDomain (mathematical analysis)Key (lock)AlgorithmPsychologyMathematicsPolitical scienceDevelopmental psychologyMathematical analysisComputer securityLawMachine Learning in HealthcareSepsis Diagnosis and TreatmentClinical Reasoning and Diagnostic Skills