Information Fusion via Symbolic Regression: A Tutorial in the Context of Human Health
This tutorial provides an incremental overview of symbolic regression for interpretable modeling in human health, targeting researchers and practitioners in health and nutrition.
The paper tackles the problem of interpretable modeling for information fusion by applying symbolic regression to estimate body fat percentage from anthropometric markers using NHANES data, resulting in a simple mathematical expression for practical use.
This tutorial paper provides a general overview of symbolic regression (SR) with specific focus on standards of interpretability. We posit that interpretable modeling, although its definition is still disputed in the literature, is a practical way to support the evaluation of successful information fusion. In order to convey the benefits of SR as a modeling technique, we demonstrate an application within the field of health and nutrition using publicly available National Health and Nutrition Examination Survey (NHANES) data from the Centers for Disease Control and Prevention (CDC), fusing together anthropometric markers into a simple mathematical expression to estimate body fat percentage. We discuss the advantages and challenges associated with SR modeling and provide qualitative and quantitative analyses of the learned models.