"My nose is running.""Are you also coughing?": Building A Medical Diagnosis Agent with Interpretable Inquiry Logics

TL;DR

This paper introduces an interpretable, data-driven dialogue system for medical diagnosis that mimics doctors' inquiry logics, improves diagnosis accuracy, and is validated on a new, large-scale dataset.

Contribution

It proposes a transparent decision process for medical dialogue systems, mimicking doctors' inquiry logics, and introduces a new high-quality dataset for training and evaluation.

Findings

Achieved up to 10% improvement in diagnosis accuracy

Developed a highly interpretable model with transparent components

Collected a large, diverse, high-quality DSMD dataset

Abstract

With the rise of telemedicine, the task of developing Dialogue Systems for Medical Diagnosis (DSMD) has received much attention in recent years. Different from early researches that needed to rely on extra human resources and expertise to help construct the system, recent researches focused on how to build DSMD in a purely data-driven manner. However, the previous data-driven DSMD methods largely overlooked the system interpretability, which is critical for a medical application, and they also suffered from the data sparsity issue at the same time. In this paper, we explore how to bring interpretability to data-driven DSMD. Specifically, we propose a more interpretable decision process to implement the dialogue manager of DSMD by reasonably mimicking real doctors' inquiry logics, and we devise a model with highly transparent components to conduct the inference. Moreover, we collect a new DSMD dataset, which has a much larger scale, more diverse patterns and is of higher quality than the existing ones. The experiments show that our method obtains 7.7%, 10.0%, 3.0% absolute improvement in diagnosis accuracy respectively on three datasets, demonstrating the effectiveness of its rational decision process and model design. Our codes and the GMD-12 dataset are available at https://github.com/lwgkzl/BR-Agent.