Multiple additive regression trees with application in epidemiology

TLDR

Predicting future outcomes from past observational data is common across many scientific fields. The study focuses on predicting various grades of cervical preneoplasia and neoplasia. The authors introduce an automated boosting‑based CART extension, Multiple Additive Regression Trees (MART), and provide tools for interpreting and visualizing its results. The MART tool is fast, off‑the‑shelf, competitive in accuracy with customized methods, requires little tuning, and is robust to noisy data. © 2003 John Wiley & Sons, Ltd.

Abstract

Abstract Predicting future outcomes based on knowledge obtained from past observational data is a common application in a wide variety of areas of scientific research. In the present paper, prediction will be focused on various grades of cervical preneoplasia and neoplasia. Statistical tools used for prediction should of course possess predictive accuracy, and preferably meet secondary requirements such as speed, ease of use, and interpretability of the resulting predictive model. A new automated procedure based on an extension (called ‘boosting’) of regression and classification tree (CART) models is described. The resulting tool is a fast ‘off‐the‐shelf’ procedure for classification and regression that is competitive in accuracy with more customized approaches, while being fairly automatic to use (little tuning), and highly robust especially when applied to less than clean data. Additional tools are presented for interpreting and visualizing the results of such multiple additive regression tree (MART) models. Copyright © 2003 John Wiley & Sons, Ltd.