Knowledge-Aware Neural Networks for Medical Forum Question Classification

TL;DR

This paper introduces MedBERT, a knowledge-aware neural network that improves classification of medical forum questions by emphasizing medical concepts and leveraging domain-specific knowledge, achieving state-of-the-art results.

Contribution

The paper presents a novel BERT-based model that incorporates medical knowledge and a new dataset for classifying medical forum questions, advancing automatic query routing.

Findings

MedBERT outperforms existing models on benchmark datasets.

It performs effectively in low-resource scenarios.

The model emphasizes medical concepts for better classification.

Abstract

Online medical forums have become a predominant platform for answering health-related information needs of consumers. However, with a significant rise in the number of queries and the limited availability of experts, it is necessary to automatically classify medical queries based on a consumer's intention, so that these questions may be directed to the right set of medical experts. Here, we develop a novel medical knowledge-aware BERT-based model (MedBERT) that explicitly gives more weightage to medical concept-bearing words, and utilize domain-specific side information obtained from a popular medical knowledge base. We also contribute a multi-label dataset for the Medical Forum Question Classification (MFQC) task. MedBERT achieves state-of-the-art performance on two benchmark datasets and performs very well in low resource settings.