Expert-Augmented Machine Learning

TL;DR

Expert-Augmented Machine Learning (EAML) integrates expert knowledge into models to enhance performance, interpretability, and generalizability, especially in critical applications like healthcare, by combining human insights with data-driven methods.

Contribution

This paper introduces EAML, a novel automated framework for extracting and integrating expert knowledge into machine learning models to improve their reliability and applicability.

Findings

EAML improves model generalization across populations.

EAML reveals hidden confounders in data.

EAML reduces data requirements for training.

Abstract

Machine Learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption by the level of trust that models afford users. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of man and machine. Here we present Expert-Augmented Machine Learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We use a large dataset of intensive care patient data to predict mortality and show that we can extract expert knowledge using an online platform, help reveal hidden confounders, improve generalizability on a different population and learn using less data. EAML presents a novel framework for high performance and dependable machine learning in critical applications.