The global research of artificial intelligence on Alzheimer disease

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Background: With the increasing global prevalence of Alzheimer disease (AD), there has been heightened attention on the onset and progression of AD. Studies indicate that artificial intelligence (AI) has demonstrated potential in the early prediction and diagnosis of AD. However, current research still falls short in terms of data diversity and the application of personalized models. Objective: This manuscript utilizes bibliometric methods to explore the application trends and emerging frontiers of AI in AD research. Methods: In the Web of Science Core Collection, we gathered documents from 1999 to 2023 focusing on the application of AI in AD. CiteSpace and VOSviewer were utilized to conduct a thorough analysis of various aspects, including countries, institutions, authors, journals, and keywords. Results: A total of 5347 articles were selected for this study. The United States of America leads this field. The University of London, Harvard University, the University of North Carolina, and the University of California are the top 4 institutions by publication volume. Daoqiang Zhang is identified as the most influential scholar in this field. NeuroImage is regarded as the most influential journal in this field. The keyword co-occurrence analysis indicates that this study focuses on the application of machine learning and deep learning (DL) in predicting and diagnosing AD. Research trends show an increasing preference for using DL in combination with multimodal data for AD classification and early diagnosis. Conclusions: AI is accelerating AD research through DL and multimodal imaging, driving progress in early diagnosis and biomarker discovery. However, challenges remain, including limited data diversity and a lack of model interpretability. Future efforts should focus on developing robust, generalizable, and clinically interpretable models by integrating diverse and longitudinal data to enable personalized diagnosis and treatment.