Introduction: Artificial intelligence (AI) and machine learning (ML) are revolutionizing surgical fields, including oculoplastic surgery. In blepharoplasty, these technologies offer objective analysis of eyelid morphology, age estimation, and surgical outcomes, potentially enhancing both cosmetic and functional results. This systematic review and meta-analysis aimed to evaluate the diagnostic performance and applications of AI/ML in blepharoplasty procedures.

Methods: Following PRISMA guidelines, four databases (PubMed, Embase, Scopus, and Web of Science) were searched through June 2025. Eligible studies included original research evaluating AI/ML tools for blepharoplasty-related assessments. Data extraction and quality assessment (NIH tool) were independently conducted by two reviewers. A diagnostic test accuracy meta-analysis was performed using MetaDisc 2.0 and RevMan 5.4.1 to pool sensitivity and specificity data, with heterogeneity assessed via I².

Results: Of 944 records identified, 12 studies met inclusion criteria. Eight were rated as good quality. Pooled analysis of four studies assessing AI-based blepharoptosis detection showed a sensitivity of 83% (95% CI: 0.67–0.92) and specificity of 84% (95% CI: 0.83–0.86). Two studies demonstrated the ability of AI models to quantify postoperative age reduction, with reductions ranging from 2 to 5 years. Five studies evaluated AI's role in eyelid morphology assessment, with several demonstrating high accuracy and reproducibility comparable to expert clinicians. Ethical concerns, particularly data diversity, were also highlighted.

Conclusion: AI and ML technologies show promising utility in blepharoplasty for diagnosing blepharoptosis, assessing eyelid morphology, and estimating rejuvenation outcomes. Further large-scale, diverse, and prospective studies are needed to support integration into clinical practice.