Utilising Deep Learning to Elicit Expert Uncertainty

TL;DR

This paper advances prior elicitation methods by applying deep learning models to real expert decision data, enabling more accurate capture of expert uncertainty in complex, non-tabular scenarios.

Contribution

It introduces a deep learning approach to improve prior elicitation from expert decisions, extending previous methods to real-world, complex data.

Findings

Deep learning models effectively model expert decision-making.

The approach captures expert uncertainty more accurately.

Application to colon cancer risk demonstrates practical utility.

Abstract

Recent work [ 14 ] has introduced a method for prior elicitation that utilizes records of expert decisions to infer a prior distribution. While this method provides a promising approach to eliciting expert uncertainty, it has only been demonstrated using tabular data, which may not entirely represent the information used by experts to make decisions. In this paper, we demonstrate how analysts can adopt a deep learning approach to utilize the method proposed in [14 ] with the actual information experts use. We provide an overview of deep learning models that can effectively model expert decision-making to elicit distributions that capture expert uncertainty and present an example examining the risk of colon cancer to show in detail how these models can be used.