End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis

TL;DR

This paper introduces an end-to-end medical diagnosis dialogue system that integrates medical knowledge graphs into conversation management, significantly improving diagnosis accuracy over existing methods.

Contribution

The work presents a novel knowledge-routed deep Q-network that incorporates medical knowledge graphs for improved dialogue topic management in diagnosis systems.

Findings

KR-DS outperforms state-of-the-art methods by over 8% in diagnosis accuracy.

The system effectively encodes symptom-disease relations for better diagnosis.

KR-DS demonstrates robustness on a challenging real-world medical dialogue dataset.

Abstract

Beyond current conversational chatbots or task-oriented dialogue systems that have attracted increasing attention, we move forward to develop a dialogue system for automatic medical diagnosis that converses with patients to collect additional symptoms beyond their self-reports and automatically makes a diagnosis. Besides the challenges for conversational dialogue systems (e.g. topic transition coherency and question understanding), automatic medical diagnosis further poses more critical requirements for the dialogue rationality in the context of medical knowledge and symptom-disease relations. Existing dialogue systems (Madotto, Wu, and Fung 2018; Wei et al. 2018; Li et al. 2017) mostly rely on data-driven learning and cannot be able to encode extra expert knowledge graph. In this work, we propose an End-to-End Knowledge-routed Relational Dialogue System (KR-DS) that seamlessly incorporates rich medical knowledge graph into the topic transition in dialogue management, and makes it cooperative with natural language understanding and natural language generation. A novel Knowledge-routed Deep Q-network (KR-DQN) is introduced to manage topic transitions, which integrates a relational refinement branch for encoding relations among different symptoms and symptom-disease pairs, and a knowledge-routed graph branch for topic decision-making. Extensive experiments on a public medical dialogue dataset show our KR-DS significantly beats state-of-the-art methods (by more than 8% in diagnosis accuracy). We further show the superiority of our KR-DS on a newly collected medical dialogue system dataset, which is more challenging retaining original self-reports and conversational data between patients and doctors.