Technical gazette, Vol. 32 No. 5, 2025.
Original scientific paper
https://doi.org/10.17559/TV-20240721001871
Regional Disparities and Evolutionary Trends in Physician Resources in China: A Deep Learning and Text Mining Approach
Siyu Wang
; School of Information Science Guangdong University of Finance and Economics, China No. 21 Xueyuan Road, Baiyun District, Guangzhou, Guangdong Province, China
Mingyang Li
orcid.org/0000-0002-8697-1398
; School of Economics and Management Changchun University of Technology, China No. 1699 Qingshan Road, Chaoyang District, Changchun, Jilin Province, China
*
Limin Wang
; School of Information Science Guangdong University of Finance and Economics, China No. 21 Xueyuan Road, Baiyun District, Guangzhou, Guangdong Province, China
*
Xuming Han
; College of Information Science and Technology Jinan University, China No. 601, Huangpu Avenue West, Tianhe District, Guangzhou, Guangdong Province, China
Jiawei Li
; School of Economics and Management Changchun University of Technology, China No. 1699 Qingshan Road, Chaoyang District, Changchun, Jilin Province, China
* Corresponding author.
Abstract
Physician resources are fundamental assets of the healthcare system. The unequal distribution of these resources inevitably leads to patients seeking medical services elsewhere, increasing healthcare costs, and hindering the realization of health equity. However, the phenomenon of uneven healthcare resource distribution is widespread, deviating from the goal of balanced regional development. Moreover, few studies have explored regional disparities and evolutionary trends in physician resources from the perspective of doctors' professional skills. To address this gap, this paper proposes a method for assessing regional differences in physician resources based on text big data, from the perspective of doctors' professional skills. The method uses a deep learning-based named entity recognition approach to extract two types of relevant entities diseases and treatment methods and assigns weights to these entities using their inverse document frequency index. The effectiveness of this method is validated through experiments, and based on large-scale online medical community text data. The proposed method is used to explore the provincial disparities and their evolutionary trends over time in physician resources in China. The results indicate that physician resources exhibit significant spatial and temporal heterogeneity. Professional skills should be taken into consideration in order to achieve a balanced, rational, and efficient distribution of physician resources.
Keywords
deep learning; evolutionary trends; physician resources; regional disparities; text mining
Hrčak ID:
335054
URI
Publication date:
30.8.2025.
Visits: 230 *