Knowledge-enhanced online doctor recommendation framework based on knowledge graph and joint learning

Abstract

A well-performed doctor recommendation system is significant for both patients and Online Medical Consultation Platforms (OMCPs). Though previous studies have proposed many doctor recommendation methods, some are overly personalized for implementation in large-scale OMCPs, while some other machine learning-based approaches perform poorly due to the simplistic information available about patients and doctors on OMCPs. This research proposes an online doctor recommendation framework based on knowledge graph (KG) and joint learning to address these problems. The framework first constructs a comprehensive medical KG, including details about doctors on the platform and a wealth of medical knowledge, to better extract features of doctors and patients. It obtains feature representations of doctors from the medical KG and extracts features from patients’ consultation texts at both sentence and word levels using word embedding and KG embedding. Finally, these features are fed into a deep neural network to calculate the recommendation probability. All processes are learned simultaneously within an overall framework. Extensive experiments conducted on four real datasets illustrate the superior performance of our model and the effectiveness of incorporating KG into doctor recommendation in providing interpretations for the recommendation results.