JMIR Publications

ABSTRACT

Background:

Online healthcare consultation provides patients with extensive access to physicians but also presents the challenge of selecting a suitable doctor without triage guidance. Patients have multi-faceted needs, prioritizing not only recommendation accuracy but also physician service quality and diversity in treatable diseases. Furthermore, the sparsity of patient interaction data intensifies the difficulty of providing balanced and effective recommendations.

Objective:

This study aims to develop a multi-objective physician recommendation method that simultaneously optimizes recommendation accuracy, service quality, and diversity of physician expertise, while addressing the data sparsity challenge inherent in online healthcare platforms.

Methods:

We propose DyGMO-PR, a dynamic graph-based multi-objective optimization method that integrates bacterial colony optimization with an evolving physician relationship graph. Our approach features a novel graph-based encoding scheme, a chemotaxis-inspired graph walking strategy for stable search, and a dynamic graph evolution mechanism that learns implicit physician relationships to enhance recommendation quality under sparse data conditions.

Results:

Evaluations on a real-world dataset show that DyGMO-PR outperforms six state-of-the-art multi-objective recommendation algorithms across all three objectives and achieves the highest hypervolume and recall values. Case studies and graph analysis further demonstrate the method's effectiveness in generating interpretable and balanced recommendation lists.

Conclusions:

DyGMO-PR offers an effective solution for multi-faceted physician recommendation, successfully balancing multiple patient preferences and mitigating data sparsity through dynamic graph learning. This work provides a flexible and practical foundation for building more responsive and reliable recommender systems in online healthcare.