Towards a Reliable and Robust Dialogue System for Medical Automatic Diagnosis

Junfan Lin, Lin Xu, Ziliang Chen, Liang Lin

Abstract: Dialogue system for medical automatic diagnosis (DSMAD) aims to learn an agent that mimics the behavior of a human doctor, i.e. inquiring symptoms and informing diseases. Since DSMAD has been formulated as a Markov decision-making process, many studies apply reinforcement learning methods to solve it. Unfortunately, existing works solely rely on simple diagnostic accuracy to justify the effectiveness of their DSMAD agents while ignoring the medical rationality of the inquiring process. From the perspective of medical application, it's critical to develop an agent that is able to produce reliable and convincing diagnosing processes and also is robust in making diagnosis facing noisy interaction with patients. To this end, we propose a novel DSMAD agent, INS-DS (Introspective Diagnosis System) comprising of two separate yet cooperative modules, i.e., an inquiry module for proposing symptom-inquiries and an introspective module for deciding when to inform a disease. INS-DS is inspired by the introspective decision-making process of human, where the inquiry module first proposes the most valuable symptom inquiry, and then the introspective module intervenes the potential responses of this inquiry and decides to inquire only if the diagnoses of these interventions vary.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=H5pv55wWSa