Imperiale, Thomas F.Monahan, Patrick O.2022-04-152022-04-152020-07Imperiale, T. F., & Monahan, P. O. (2020). Risk Stratification Strategies for Colorectal Cancer Screening: From Logistic Regression to Artificial Intelligence. Gastrointestinal Endoscopy Clinics of North America, 30(3), 423–440. https://doi.org/10.1016/j.giec.2020.02.004https://hdl.handle.net/1805/28502Risk stratification is a system or process by which clinically-meaningful separation of risk is achieved in a group of otherwise similar persons. While parametric logistic regression dominates risk prediction, use of nonparametric methods such as classification and regression trees, artificial neural networks, and other machine-learning methods are increasing. Collectively, these learning methods are referred to as “artificial intelligence” (AI). The persuasive nature of AI requires knowledge of study validity, an understanding of model metrics, and determination of whether and to what extent the model can and should be applied to the patient or population under consideration. Further investigation is needed, especially in model validation and impact assessment.enPublisher Policyrisk stratificationcolorectal cancer screeningrisk prediction modelsArticle