Towards knowledge-infused automated disease diagnosis assistant

Abstract

With the advancement of internet communication and telemedicine, people are increasingly turning to the web for various healthcare activities. With an ever-increasing number of diseases and symptoms, diagnosing patients becomes challenging. In this work, we build a diagnosis assistant to assist doctors, which identifies diseases based on patient-doctor interaction. During diagnosis, doctors utilize both symptomatology knowledge and diagnostic experience to identify diseases accurately and efficiently. Inspired by this, we investigate the role of medical knowledge in disease diagnosis through doctor-patient interaction. We propose a two-channel, knowledge-infused, discourse-aware disease diagnosis model (KI-DDI), where the first channel encodes patient-doctor communication using a transformer-based encoder, while the other creates an embedding of symptom-disease using a graph attention network (GAT). In the next stage, the conversation and knowledge graph embeddings are infused together and fed to a deep neural network for disease identification. Furthermore, we first develop an empathetic conversational medical corpus comprising conversations between patients and doctors, annotated with intent and symptoms information. The proposed model demonstrates a significant improvement over the existing state-of-the-art models, establishing the crucial roles of (a) a doctor's effort for additional symptom extraction (in addition to patient self-report) and (b) infusing medical knowledge in identifying diseases effectively. Many times, patients also show their medical conditions, which acts as crucial evidence in diagnosis. Therefore, integrating visual sensory information would represent an effective avenue for enhancing the capabilities of diagnostic assistants.

Figure 1

An illustration of online symptom investigation and disease diagnosis.

Figure 2

A dialogue sample from the curated Empathical dataset. Conversation between patient and doctor having symptom and intent tagged.

Figure 3

KI-DDI: Self Report and Dialog are passed through the language model to obtain their embedding. The blue nodes are symptoms and Red nodes are diseases linked to symptoms. A joint Graph is formed by connecting the dialog node to all symptom nodes.

Algorithm 1

Discourse-aware selective filtering (DSF)

Figure 4

Disease diagnosis accuracy of different models.

Figure 5

Performance of KI-DDI and other models on a common test case.

Figure 6

Distribution of attention scores for two test examples.

Figure 7

Performance of KI-DDI model upon varying layers.