Key points are not available for this paper at this time.
Abstract Chronic kidney disease (CKD) is a global public health problem characterized by persistent kidney damage or loss of kidney function. Previously, the diagnosis of CKD has mainly relied on serum creatinine and estimation of the glomerular filtration rate. However, with the development and progress of artificial intelligence (AI), AI has played different roles in various fields, such as early diagnosis, progression prediction, prediction of associated risk factors, and drug safety and efficacy evaluation. Therefore, research related to the application of AI in the field of CKD has become a hot topic at present. Therefore, this study adopts a bibliometric approach to study and analyze the development and evolution patterns and research hotspots of AI-CKD. English publications related to the field between January 1, 2004, and June 27, 2024, were extracted from the Web of Science Core Collection database. The research hotspots and trends of AI-CKD were analyzed at multiple levels, including publication trends, authors, institutions, countries, references and keywords, using VOSviewer and CiteSpace. The results showed that a total of 203 publications on AI-CKD were included in the study, of which Barbieri Carlo from the University of Milan, Italy, had the highest number of publications (NP=5) and had a high academic impact (H-Index=5), while the USA and its institution, the Mayo Clinic, were the publications. The USA and its Mayo Clinic are the countries and institutions with the highest number of publications, and China is the country with the second highest number of publications, with three institutions attributed to China among the top five institutions. Germany’s institution, Fresenius Medical Care, has the highest academic impact (H-index=6). Keyword analysis yielded artificial intelligence, chronic kidney disease, machine learning, prediction model, risk, deep learning, and other keywords with high frequency, and cluster analysis based on the timeline yielded a total of 8 machine learning, deep learning, retinal microvascular abnormality, renal failure, Bayesian network, anemia, bone disease, and allograft nephropathology clusters. This study provides a comprehensive overview of the current state of research and global frontiers of AI-CKD through bibliometric analysis. These findings can provide a valuable reference and guidance for researchers.
Li et al. (Thu,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: