Advancements in artificial intelligence for meibography: clinical utility and contributions to meibomian gland dysfunction management
Clinical Snapshot
PICO Framework
| P — Population | Patients with suspected or confirmed meibomian gland dysfunction |
| I — Intervention | AI-based meibography systems for gland assessment |
| C — Comparator | Traditional meibography or clinical assessment methods |
| O — Outcomes | Diagnostic accuracy, gland morphology quantification, disease staging, clinical utility measures |
Bottom Line
This narrative review examines AI applications in meibography for assessing meibomian gland dysfunction but lacks the rigorous methodology expected of a systematic review. While the topic is clinically relevant—MGD affects up to 86% of patients with dry eye disease—the review provides limited quantitative evidence to guide clinical decision-making. The authors acknowledge significant limitations including restricted dataset diversity and lack of standardised protocols. Key gaps include absence of diagnostic accuracy data, cost-effectiveness analysis, and comparison with standard clinical assessment. The substantial industry involvement raises concerns about potential bias. Clinicians should await more robust systematic reviews and validation studies before adopting AI-enhanced meibography in routine practice.
Key Findings
Effect Size: Not reported
Primary Outcome: AI enables objective quantitative assessment of meibomian gland structure
Nnt Or Sensitivity: Diagnostic accuracy measures not quantified
Confidence Interval: Not provided
Clinical Application
Limited by need for specialised equipment and software validation Relevant to Australian optometrists and ophthalmologists, though TGA approval status of AI-enhanced meibography systems unclear Patients with dry eye disease and suspected MGD in optometry and ophthalmology practices
Abstract
Recent advances in artificial intelligence (AI) have enhanced the capabilities of meibography by enabling objective and quantitative assessment of meibomian gland structure. This review explores the clinical utility of AI-based meibography in the diagnosis and management of Meibomian Gland Dysfunction (MGD), with a focus on segmentation, morphological analysis, and disease staging. Developments in deep learning have enabled more precise gland feature extraction, including gland dropout, density, and tortuosity, supporting efforts towards standardised and reproducible clinical evaluation. Although not the focus of this review, insights from traditional image processing techniques are referenced to highlight potential areas of improvement in current AI models. Key issues such as limited modelling of regional gland variation, restricted dataset diversity, and lack of standardised image quality control are discussed. Although significant progress has been made, further work is needed to ensure AI-driven meibography tools are generalisable, interpretable, and suitable for broad clinical implementation.
References
- 1.Swiderska, K., Blackie, C. A., Murakami, D., Appenteng, E. O., Read, M. L., Maldonado-Codina, C., & Morgan, P. B. (2026). Advancements in artificial intelligence for meibography: clinical utility and contributions to meibomian gland dysfunction management. Clinical & Experimental Optometry, 109(4), 123-135. https://doi.org/10.1080/08164622.2025.2555315
Related Research
PloS one
Fundus image analysis of retinitis pigmentosa using artificial intelligence
25 July 2026
PloS one
AI-based color vision screening and educational counseling for high school students: An experimental study
24 July 2026
Medical image analysis
STAGE challenge: Structural-Functional Transition in Glaucoma Assessment
3 July 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service