ABSTRACT Computer vision, enabled by machine learning and image processing techniques, plays a crucial role in healthcare by facilitating the analysis of medical images such as magnetic resonance imaging, computed tomography and X‐rays. It supports disease diagnosis, treatment planning, telemedicine and remote patient monitoring. Despite rapid growth, research in this field remains fragmented, making it difficult to comprehensively understand its evolution and research patterns. This study aimed to systematically analyse global research trends in computer vision applications in healthcare using bibliometric methods. A bibliometric analysis was conducted on 1023 publications retrieved from the Web of Science (Wos) database published between 2000 and 2022. Scientific output, citation patterns, leading journals, authors, institutions, countries, funding agencies and research themes were analysed using VOSviewer, Biblioshiny and ScientoPy. The annual scientific output showed a consistent upward trend, with a peak in 2021. IEEE Access emerged as the most productive journal (90 publications), while IEEE transactions on medical imaging was the most cited source. China led in publication output and international collaboration, followed by the United States. Keyword analysis revealed dominant themes such as deep learning, image segmentation, classification and medical imaging. This bibliometric analysis provides a comprehensive overview of the intellectual structure, research hotspots and collaborative patterns in computer vision–based healthcare research. The findings offer valuable insights for researchers, clinicians and policymakers and identify potential directions for future investigations.
Issrani et al. (Thu,) studied this question.