Risk Stratification Strategies for Colorectal Cancer Screening : From Logistic Regression to Artificial Intelligence - 19/05/20

Doi : 10.1016/j.giec.2020.02.004

Thomas F. Imperiale, MD ^a,^c,^d,^e,^⁎ , Patrick O. Monahan, PhD ^b,^e,^f
^a Department of Medicine, Indiana University School of Medicine, Indianapolis, IN, USA
^b Department of Biostatistics, Indiana University School of Medicine and Richard M. Fairbanks School of Public Health, Indianapolis, IN, USA
^c Health Services Research and Development, Richard L. Roudebush VA Medical Center, Indianapolis, IN, USA
^d Regenstrief Institute, Inc., 1101 West 10th Street, Indianapolis, IN 46202, USA
^e Indiana University Melvin and Bren Simon Cancer Center, Indiana University School of Medicine, Indianapolis, IN, USA
^f Health Information and Translational Sciences, 410 West 10th Street Suite 3000, Indianapolis, IN 46202, USA

^∗Corresponding author. Regenstrief Institute, Inc., 1101 West 10th Street, Indianapolis, IN 46202.Regenstrief Institute, Inc.1101 West 10th StreetIndianapolisIN46202

Résumé

Risk stratification is a system by which clinically meaningful separation of risk is achieved in a group of otherwise similar persons. Although parametric logistic regression dominates risk prediction, use of nonparametric and semiparametric methods, including artificial neural networks, is increasing. These statistical-learning and machine-learning methods, along with simple rules, are collectively referred to as “artificial intelligence” (AI). AI requires knowledge of study validity, 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.

Le texte complet de cet article est disponible en PDF.

Keywords : Risk stratification, Colorectal cancer screening, Risk prediction models, Cancer prevention, Multivariate methods, Machine learning methods