A bibliometric analysis of global trends in AI-driven digital health technologies for diabetes management

Clinical Snapshot

Key Findings

• P Value: Not reported — no inferential statistical testing conducted

• Effect Size: Not applicable — bibliometric study; no clinical effect size calculable

• Primary Outcome: 673 publications identified on AI-driven digital health technologies for diabetes management in WoSCC up to July 12, 2025, with a steady increase in global publication volume over time

• Nnt Or Sensitivity: Not applicable — three keyword clusters identified: (1) AI-enabled monitoring, (2) digital health interventions, (3) AI-based diabetic retinopathy screening. USA led in publication output; University of London was most productive institution; Sensors and Diabetes Care were most frequently published/cited journals; most-cited article was the Gulshan et al. deep learning diabetic retinopathy paper (JAMA, 2016)

• Confidence Interval: Not reported — bibliometric methodology does not generate confidence intervals

Clinical Application

The research mapping function of this study is feasible to use for research prioritisation and grant strategy. However, direct clinical implementation decisions should not be based on bibliometric evidence alone. Clinicians should seek systematic reviews and randomised controlled trials for practice-changing decisions in AI-assisted diabetes management. Australia has a significant and growing diabetes burden, with approximately 1.3 million Australians living with diagnosed diabetes (AIHW). The three research hotspots identified — AI-enabled continuous glucose monitoring, digital health interventions, and AI-based diabetic retinopathy screening — are directly relevant to Australian practice. The TGA has begun regulatory engagement with AI-based medical devices (Software as a Medical Device, SaMD framework). The RACGP Standards for General Practice and the National Diabetes Strategy 2021–2030 both emphasise technology-enabled care and early complication screening. PBS-listed continuous glucose monitoring (CGM) for eligible patients with Type 1 diabetes reflects the clinical translation of monitoring technologies identified as a research hotspot. Australian clinicians should note that bibliometric prominence does not equate to TGA approval or PBS listing eligibility for specific AI tools. This bibliometric study does not directly apply to a clinical patient population. Its findings are relevant to researchers, health informaticians, diabetes educators, and clinical policy makers seeking to understand the trajectory of AI and digital health research in diabetes care.

Abstract

BACKGROUND: Digital health technologies are increasingly applied in diabetes care, enabling continuous monitoring, personalized support and remote interventions. Meanwhile, artificial intelligence (AI) is enhancing the precision and effectiveness of these tools. This study aims to map global research trends and thematic developments in AI-driven digital health technologies for diabetes management and to explore their future directions. METHODS: We collected data from the Web of Science Core Collection, including articles and reviews published up to July 12, 2025, using CiteSpace, VOSviewer, and Microsoft Excel to analyze countries/regions, institutions, journals, references, authors, and keywords. RESULTS: A total of 673 publications were included in the analysis. Global publications on AI-driven digital health technologies for diabetes increased steadily, with the USA leading in output. The University of London ranked as the most productive institution. Sensors and diabetes care were the most frequently published and cited journals in this field. Herrero P was among the most prolific authors. The most cited article was "Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs." "diabetes" was the most frequently occurring keyword. Keyword cluster analysis identified 3 primary research hotspots: AI-enabled monitoring, digital health interventions, and AI-based diabetic retinopathy screening. CONCLUSIONS: This study summarizes the evolution of AI-driven digital health technologies in diabetes care. Although challenges remain in data security, standardization and validation, these technologies hold increasing potential for accurate diagnosis, real-time monitoring and personalized care.

References

1. 1.Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., Kim, R., Raman, R., Nelson, P. C., Mega, J. L., & Webster, D. R. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 316(22), 2402–2410. https://doi.org/10.1001/jama.2016.17216
2. 2.Song, J., Tao, W., Zhou, D., Li, X., Peng, S., Li, C., & Yuan, J. (2026). A bibliometric analysis of global trends in AI-driven digital health technologies for diabetes management. Medicine, advance online publication. https://doi.org/10.1097/MD.0000000000049815