Online physician recommendation with dynamic capacity and semantic similarity: A primal-dual optimization framework
6 affiliations
- 1School of Economics and Management, Jiangsu University of Science and Technology, Zhenjiang, Jiangsu, China
- 2School of Business, Anhui University, Hefei, Anhui, China
- 3Department of Pathology, First Affiliated Hospital of Soochow University, Suzhou, China
- 4School of Economics and Management, Wuhan University, Wuhan, Hubei, China
- 5School of Management, Hefei University of Technology, Hefei, Anhui, China
- 6School of Economics and Management, Southeast University, Nanjing, Jiangsu, China
Abstract
Existing physician recommendation methods mostly start from the patient’s perspective on online healthcare platforms, neglecting the importance of physician service capacity and semantic similarity. Considering the uncertainty of arrivals and capacity constraints, this study aims to propose a dynamic capacity and semantic similarity-based framework to recommend physicians. We design an online rolling matching algorithm based on delayed decision-making. We employ MPNet, a pre-trained language model based on masked and permuted language modeling, to extract contextual semantic representations from unstructured consultation records and construct physician-patient matching quality. The proposed method is validated using a real-world dataset with 88,009 records from one of the largest online healthcare platforms in China. The results show that our method significantly outperforms baseline methods. It achieves competitive ratio of approximately 0.988 on both CIM and HS datasets, with the largest improvement reaching 0.094 over the baseline methods. The improvements over all baselines are statistically significant. The sensitivity and robustness analysis further demonstrate that the integration of dynamic capacity constraints and MPNet-based semantic similarity enhances the effectiveness and stability of online physician recommendation. This study provides a reliable reference for users to find online physicians and offers practical implications for the design of online healthcare platforms. The implementation of our method is available at https://github.com/qiuyan-just/dynamic_matching to facilitate reproducibility.
Related
- Evidence-to-Recommendation Framework for 2026 ACE Clinical Guideline on allergic rhinitis — diagnosis and management
- Exploring barriers and facilitators for non-communicable disease care for persons living with HIV in Peru through a socioecological framework: HIV physician and coordinator perspectives
- Whole genome similarity provides a rapid, robust framework for classification of fungal taxa from the genus rank to intraspecies variants
- RDEmbed: A Sentence-Embedding Framework for Rare Disease Phenotype Representation and Phenotypic Similarity Analysis
- From T-cell renewal to immune longevity: a multilevel capacity framework for immune aging
BibTeX
@article{qiu2026online,
title = {{Online physician recommendation with dynamic capacity and semantic similarity: A primal-dual optimization framework}},
author = {Yan Qiu and Yi Chen and Yinghong Xie and Min Li and Junhui Yan and Hu Liu},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0357449},
url = {https://doi.org/10.1371/journal.pone.0357449},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Online physician recommendation with dynamic capacity and semantic similarity: A primal-dual optimization framework
AU - Yan Qiu
AU - Yi Chen
AU - Yinghong Xie
AU - Min Li
AU - Junhui Yan
AU - Hu Liu
PY - 2026
DA - 2026/09/15
JO - PLOS One
DO - 10.1371/journal.pone.0357449
UR - https://doi.org/10.1371/journal.pone.0357449
AB - Existing physician recommendation methods mostly start from the patient’s perspective on online healthcare platforms, neglecting the importance of physician service capacity and semantic similarity. Considering the uncertainty of arrivals and capacity constraints, this study aims to propose a dynamic capacity and semantic similarity-based framework to recommend physicians. We design an online rolling matching algorithm based on delayed decision-making. We employ MPNet, a pre-trained language model based on masked and permuted language modeling, to extract contextual semantic representations from unstructured consultation records and construct physician-patient matching quality. The proposed method is validated using a real-world dataset with 88,009 records from one of the largest online healthcare platforms in China. The results show that our method significantly outperforms baseline methods. It achieves competitive ratio of approximately 0.988 on both CIM and HS datasets, with the largest improvement reaching 0.094 over the baseline methods. The improvements over all baselines are statistically significant. The sensitivity and robustness analysis further demonstrate that the integration of dynamic capacity constraints and MPNet-based semantic similarity enhances the effectiveness and stability of online physician recommendation. This study provides a reliable reference for users to find online physicians and offers practical implications for the design of online healthcare platforms. The implementation of our method is available at https://github.com/qiuyan-just/dynamic_matching to facilitate reproducibility.
SN - 1932-6203
ER -