Answers are grounded in this paper and cite their sources.
Introduction Pulmonary embolism (PE) remains a leading cause of cardiovascular morbidity and death worldwide. A growing body of research has investigated artificial intelligence (AI) for the diagnosis, risk stratification and prognostication of PE, yet the global research landscape of this field has not been systematically mapped. Methods This study included 590 relevant articles on AI in the field of PE from the Web of Science Core Collection and Scopus databases. Bibliometric methods, combined with R software, VOSviewer, and CiteSpace, were used to perform a visual analysis of the retrieved data. Results Annual output grew slowly between 2006 and 2017 (62 articles, 10.5% of the total) and accelerated markedly from 2018 onwards; 375 articles (63.6%) were published between 2023 and 2025, and output in 2025 was approximately 14 times that in 2017 (exponential fit, R 2 = 0.876). The 590 articles involved 3,844 authors and 1,377 institutions from 63 countries/regions. The United States (257 articles, 9,791 citations) and China (117 articles, 1,320 citations) were the most productive countries, whereas citations per article were highest for Germany and the United States among the top 10. Author keywords clustered around diagnosis and imaging of PE, and recent burst keywords were “prediction” and “risk factors”. Conclusion Bibliometric mapping of 590 articles published between 2006 and 2025 shows that research on AI in PE has entered a phase of rapid growth, is dominated by a small number of countries and institutions, and remains concentrated on imaging-based diagnosis rather than on validated clinical deployment. Although several models have shown promising discriminative performance in single- or few-centre studies, the available evidence does not yet establish clinical effectiveness or improved patient outcomes. Prospective, multicentre and externally validated studies, together with multidisciplinary and cross-national collaboration, are therefore required before AI tools can be integrated into routine PE care.
No takes yet. Share an insight, caveat, or question.
Xiong et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: