To investigate the outcomes and prognosis of macular epiretinal membrane (ERM) after pars plana vitrectomy (PPV) in patients with high myopia (HM), focusing on the optimal timing of surgery and its impact on prognosis.

The clinical data of 50 eyes from 49 patients diagnosed with ERM, who were highly myopic and underwent PPV were retrospectively analyzed. The patients with ERM were classified into five groups based on the characteristics associated with different levels of myopic traction maculopathy. Group 1: Simple ERM without complex vertical and tangential direction traction on retina on optical coherence tomography (OCT) image; Group 2: ERM with obvious macular foveal schisis, without macular hole (MH); Group 3: ERM with inner lamellar MH, with or without macular foveal schisis; Group 4: ERM with outer lamellar MH, with or without foveal retinal detachment (RD); Group 5: ERM with full-thickness MH. Baseline characteristics, changes in best corrected visual acuity (BCVA) before and after surgery, and anatomical characteristics through spectral domain OCT were compared.

The 50 eyes were followed for 6mo, with an average age of 58.66y and an average axial length (AL) of 28.69 mm. Among the five groups, postoperative logMAR BCVA improved (P<0.05). Group 1 had better mean BCVA at baseline (0.59±0.36) and at 6mo postoperatively (0.16±0.22) compared to the other groups, while Group 5 had worse mean BCVA at baseline (1.68±0.45) and at 6mo postoperatively (1.27±0.64). There were no statistically significant differences in sex, age or AL between the groups (P>0.05). OCT showed that Groups 4 and 5 exhibited poorer macular anatomy compared to the other three groups, as evidenced by lower rates of central retinal reattachment (64.3% in Group 4, 86.7% in Group 5) and integrity of the inner segment/outer segment of photoreceptor junction (28.6% in Group 4, 26.7% in Group 5).

PPV is an effective treatment for ERM in patients with HM. All groups showed postoperative improvement in BCVA compared to preoperative levels, demonstrating the necessity of surgical intervention. Early intervention, particularly before the fourth stage of the disease, may lead to better visual outcomes.

To evaluate the clinical application value of the artificial intelligence assisted pathologic myopia (PM-AI) diagnosis model based on deep learning.

A total of 1156 readable color fundus photographs were collected and annotated based on the diagnostic criteria of Meta-pathologic myopia (PM) (2015). The PM-AI system and four eye doctors (retinal specialists 1 and 2, and ophthalmologists 1 and 2) independently evaluated the color fundus photographs to determine whether they were indicative of PM or not and the presence of myopic choroidal neovascularization (mCNV). The performance of identification for PM and mCNV by the PM-AI system and the eye doctors was compared and evaluated via the relevant statistical analysis.

For PM identification, the sensitivity of the PM-AI system was 98.17%, which was comparable to specialist 1 (P=0.307), but was higher than specialist 2 and ophthalmologists 1 and 2 (P<0.001). The specificity of the PM-AI system was 93.06%, which was lower than specialists 1 and 2, but was higher than ophthalmologists 1 and 2. The PM-AI system showed the Kappa value of 0.904, while the Kappa values of specialists 1, 2 and ophthalmologists 1, 2 were 0.968, 0.916, 0.772 and 0.730, respectively. For mCNV identification, the AI system showed the sensitivity of 84.06%, which was comparable to specialists 1, 2 and ophthalmologist 2 (P>0.05), and was higher than ophthalmologist 1. The specificity of the PM-AI system was 95.31%, which was lower than specialists 1 and 2, but higher than ophthalmologists 1 and 2. The PM-AI system gave the Kappa value of 0.624, while the Kappa values of specialists 1, 2 and ophthalmologists 1 and 2 were 0.864, 0.732, 0.304 and 0.238, respectively.

In comparison to the senior ophthalmologists, the PM-AI system based on deep learning exhibits excellent performance in PM and mCNV identification. The effectiveness of PM-AI system is an auxiliary diagnosis tool for clinical screening of PM and mCNV.