Epiretinal membrane (ERM) is a common retinal pathology associated with progressive visual impairment, requiring timely and accurate assessment. Recent advances in artificial intelligence (AI) have enabled automated approaches for ERM detection, segmentation, and postoperative best corrected visual acuity (BCVA) prediction, offering promising avenues to enhance clinical efficiency and diagnostic precision. We conducted a comprehensive literature search across MEDLINE (via PubMed), Scopus, CENTRAL, ClinicalTrials.gov, and Google Scholar from the inception to 31 December 2023. A total of 42 studies were included in the systematic review, with 16 eligible for meta-analysis. Risk of bias and reporting quality were assessed using the QUADAS-2 and CLAIM tools. Meta-analysis of 16 studies (533,674 images) showed that deep learning (DL) models achieved high diagnostic accuracy (AUC = 0.97), with pooled sensitivity and specificity of 0.93 and 0.97, respectively. Optical coherence tomography (OCT)-based models outperformed fundus-based ones, and although performance remained high under external validation, the positive predictive value (PPV) declined—highlighting the importance of testing model generalizability. To the best of our knowledge, this is the first systematic review and meta-analysis to critically evaluate the role of AI in the detection, segmentation, and postoperative BCVA prediction of ERM across various ophthalmic imaging modalities. Our findings provide a clear overview of current evidence supporting the continued development and clinical adoption of AI tools for ERM diagnosis and management.

Background and Clinical Significance: This paper presents a case of Vogt–Koyanagi–Harada (VKH)-like disease following nivolumab and ipilimumab therapy for squamous cell carcinoma of the lung, complicated by transient type 1 macular neovascularisation (MNV). Case Presentation: A 67-year-old man presented with reduced visual acuity, more pronounced in the left eye, accompanied by headache and neurosensory hearing loss for 10 days. He had been receiving combination therapy with nivolumab and ipilimumab for approximately nine weeks. Slit-lamp examination and multimodal imaging revealed multiple serous retinal detachments, choroidal folds, and bacillary layer detachment. A bilateral VKH-like syndrome was considered the most likely diagnosis, consistent with an immune-related adverse event (irAE). High-dose systemic corticosteroids were initiated, resulting in marked anatomical improvement and recovery of visual acuity. Following multidisciplinary discussion with the patient’s oncologist, ipilimumab was permanently discontinued and nivolumab was rechallenged in combination with chemotherapy after resolution of the ocular adverse events, given the progression of the underlying malignancy. Notably, optical coherence tomography angiography (OCTA) additionally demonstrated a type 1 non-exudative MNV, which resolved spontaneously during follow-up. Conclusions: Nivolumab and ipilimumab, targeting PD-1 and CTLA-4, respectively, are effective anticancer therapies but may induce immune-related adverse events involving the eye. VKH-like disease is a rare but potentially vision-threatening complication. Early recognition and prompt treatment are essential for favourable visual outcomes. In summary, this is a rare case of VKH-like disease associated with nivolumab and ipilimumab therapy, complicated by transient inflammatory type 1 MNV. Clear guidelines are needed regarding management of ocular immune-related adverse events and decisions on continuation or discontinuation of life-prolonging immunotherapy.