Application and prospect of artificial intelligence in metabolic associated fatty liver disease based on bibliometrics
- VernacularTitle:基于文献计量学探讨人工智能在代谢相关脂肪性肝病中的应用及展望
- Author:
Anqi LI
1
;
Peiran ZHAO
;
Yuqiang ZHAO
;
Rui WANG
;
Jing YANG
Author Information
- Publication Type:Research Article
- Keywords: bibliometrics; artificial intelligence; metabolic associated fatty liver disease; intelligent assisted diagnosis; machine learning; deep learning
- From: Journal of Clinical Medicine in Practice 2024;28(5):1-9
- CountryChina
- Language:Chinese
- Abstract: Objective To explore the application and prospects of artificial intelligence (AI) in metabolic associated fatty liver disease (MAFLD) based on bibliometrics. Methods Relevant literature on the application of AI technology in MAFLD was retrieved from the Web of Science Core Collection (WoSCC) database. Bibliometric analysis was conducted using CiteSpace, VOSviewer, R package "bibliometrix", and online bibliometric analysis was platformed to identify hotspots and trends in this field. Results A total of 303 eligible articles were obtained. Since 2017, the number of papers in this field had experienced explosive growth. The United States was leading the research on the application of AI in MAFLD and was the most frequent participant in international cooperation. San Diego of University of California was the institution with the highest number of publications. Rohit Loomba was the author with the highest number of publications, having published 14 articles. The co-cited keyword clustering labels revealed 10 major clusters: digital image analysis, machine learning, computer-aided diagnosis, fibrosis stage, automated quantitative analysis, metaproteomics, non-invasive diagnosis, ultrasonography, electronic health records, and knowledge representation. Current research on the application of AI in MAFLD mainly focused on the diagnosis, differential diagnosis, and staging of MAFLD. Image recognition and analysis, intelligent assisted diagnosis, AI algorithms, and monitoring disease progression will be important research directions for AI in MAFLD. Conclusion Research on the application of AI in MAFLD is experiencing exponential growth. Given enormous potential and clinical application prospects of this field, the application of AI in MAFLD-related areas will remain a research hotspot in the future.
