Bibliometric and visual analysis of artificial intelligence applications in pneumoconiosis and its complications
- VernacularTitle:人工智能在尘肺病及并发症领域应用的文献计量和可视化分析
- Author:
Yu FU
1
;
Xiangpei LYU
1
;
Tao LI
1
;
Huanqiang WANG
1
Author Information
- Publication Type:Investigation
- Keywords: pneumoconiosis; artificial intelligence; computer-aided diagnosis; visual analysis
- From: Journal of Environmental and Occupational Medicine 2025;42(10):1216-1224
- CountryChina
- Language:Chinese
-
Abstract:
Background Pneumoconiosis, a group of lung disease caused by long-term inhalation of occupational dust, features progressive development, irreversibility, and a high incidence of complications. It seriously endangers the health of the occupational population and exacerbates the socioeconomic burden. Objective To understand the development and major research themes of artificial intelligence research concerning pneumoconiosis and its complications. Methods Relevant academic papers before 2024-10-01 were retrieved from China National Knowledge Infrastructure and Web of Science, and analyzed separately according to the author, institutions, and keywords, then visualized with Citespace, the Bibliometrix package in R, and VOSviewer software. Results This study included
1068 articles (208 Chinese and 860 English). The results showed that artificial intelligence application in pneumoconiosis and its complications has seen explosive growth in the past five years. Institutions were mainly concentrated in universities and their affiliated medical units. Identified research hotspots included medical image recognition and analysis, auxiliary diagnosis, and risk prediction. Keywords like artificial intelligence, tuberculosis, deep learning, chronic obstructive pulmonary disease, and machine learning showed high centrality. Conclusion As computer technology advances, the use of artificial intelligence in addressing pneumoconiosis and its related complications is steadily expanding. Its research perspective has gradually expanded from simple disease prediction to diversified fields such as image recognition and health monitoring. Early pneumoconiosis screening, auxiliary differential diagnosis, andhealth monitoring will be the focus of future research.
