Extending Models Via Gradient Boosting: An Application to Mendelian Models

TL;DR

This paper introduces a method combining gradient boosting with existing models to enhance prediction accuracy, demonstrated on Mendelian genetic risk models and real cancer genetics data.

Contribution

It presents a general approach to improve existing models by integrating gradient boosting, applicable to complex models like Mendelian genetic risk predictions.

Findings

Gradient boosting improves Mendelian model performance.

The combined model outperforms standalone models.

Application to real genetic data validates the approach.

Abstract

Improving existing widely-adopted prediction models is often a more efficient and robust way towards progress than training new models from scratch. Existing models may (a) incorporate complex mechanistic knowledge, (b) leverage proprietary information and, (c) have surmounted barriers to adoption. Compared to model training, model improvement and modification receive little attention. In this paper we propose a general approach to model improvement: we combine gradient boosting with any previously developed model to improve model performance while retaining important existing characteristics. To exemplify, we consider the context of Mendelian models, which estimate the probability of carrying genetic mutations that confer susceptibility to disease by using family pedigrees and health histories of family members. Via simulations we show that integration of gradient boosting with an existing Mendelian model can produce an improved model that outperforms both that model and the model built using gradient boosting alone. We illustrate the approach on genetic testing data from the USC-Stanford Cancer Genetics Hereditary Cancer Panel (HCP) study.