A Hybrid Recommender System for Patient-Doctor Matchmaking in Primary Care
This work addresses patient-doctor matchmaking in primary care, but it is incremental as it builds on existing recommender system techniques for a specific healthcare application.
The paper tackles the problem of matching patients with family doctors in primary care by designing a hybrid recommender system that models patient trust using consultation histories and temporal dynamics, resulting in higher predictive accuracy compared to heuristic and collaborative filtering baselines.
We partner with a leading European healthcare provider and design a mechanism to match patients with family doctors in primary care. We define the matchmaking process for several distinct use cases given different levels of available information about patients. Then, we adopt a hybrid recommender system to present each patient a list of family doctor recommendations. In particular, we model patient trust of family doctors using a large-scale dataset of consultation histories, while accounting for the temporal dynamics of their relationships. Our proposed approach shows higher predictive accuracy than both a heuristic baseline and a collaborative filtering approach, and the proposed trust measure further improves model performance.