The AI platform showed clinically relevant predictive performance for preoperative and later postoperative visual outcomes after FTMH surgery, particularly at 6 and 12 months, but was less reliable in the early postoperative period.
Abstract
Objectives This study evaluated the clinical utility of a multimodal large language model-based artificial intelligence (AI) model in predicting postoperative visual outcomes following full-thickness macular hole (FTMH) surgery using the inverted internal limiting membrane (ILM) flap technique. Methods A retrospective analysis was conducted on 45 patients who underwent pars plana vitrectomy for FTMH at a tertiary eye care center between January 2021 and December 2023. Preoperative optical coherence tomography (OCT) images, demographic data, and clinical parameters were analyzed using the AI model to predict best-corrected visual acuity (BCVA) at four postoperative time points. The predicted BCVA values were then compared with actual clinical outcomes. Results Preoperatively, the mean AI-predicted BCVA was 1.13±0.20 logMAR compared with the actual value of 1.24±0.33 logMAR (p=0.192). At 6 months, the predicted BCVA was 0.65±0.20 logMAR versus the actual value of 0.67±0.25 logMAR (p=0.528), and at 12 months, it was 0.47±0.17 logMAR versus 0.55±0.27 logMAR (p=0.155). However, at 7 days postoperatively, the model significantly overestimated visual impairment, predicting 1.37±0.28 logMAR versus the actual value of 1.07±0.33 logMAR (p<0.001). Spearman correlation analysis showed the strongest association between AI-predicted and actual BCVA at 6 months (rs=0.5885, p<0.001), with a moderate correlation at 12 months (rs=0.4156, p=0.005), a weak correlation preoperatively (rs=0.3029, p=0.043), and no significant correlation at 7 days (rs=0.1949, p=0.199). Conclusion These findings demonstrate the model’s potential as a supportive tool for visual outcome prediction after FTMH surgery. The AI platform showed clinically relevant predictive performance for preoperative and later postoperative visual outcomes after FTMH surgery, particularly at 6 and 12 months, but was less reliable in the early postoperative period.
Purpose: The purpose of the study was to evaluate the anatomical and functional outcomes of the inverted internal limiting membrane (ILM) flap technique in patients with large macular holes (MHs) and identify independent prognostic factors that predict post-operative visual acuity. Methods: This retrospective study included 48 eyes of 48 patients who underwent pars plana vitrectomy and inverted ILM flap technique for idiopathic MHs ≥400 μm. Pre-operative and post-operative best-corrected visual acuity (BCVA), swept-source optical coherence tomography (SS-OCT) parameters, and various clinical factors were evaluated. Multivariate regression analysis was performed to identify independent prognostic factors for the post-operative BCVA. Results: The mean BCVA improved significantly from 1.27±0.41 logMAR preoperatively to 0.62±0.37 logMAR at 6 months postoperatively (p<0.001). U-shaped closure was associated with better BCVA than V-and W-shaped closures (p=0.001). Patients with symptom duration ≤6 months and complete post-operative restoration of the external limiting membrane (ELM) and ellipsoid zone demonstrated significantly better BCVA (p<0.01). Pre-operative BCVA (β=0.637, p<0.001) and MH index (MHI) (β=−0.261, p=0.029) were significant independent determinants of post-operative BCVA. Conclusion: The inverted ILM flap technique provides high anatomical closure rates and significant visual improvement in large MH surgery. Pre-operative BCVA and MHI were significant independent prognostic factors for post-operative visual outcomes. Structural SS-OCT parameters can be clinically useful in predicting post-operative functional outcomes
Güzide Akçay, Dilber Çelik Yaprak, U. Kıvrak et al.· European Eye Research· 0 citations
Background: To evaluate anatomical and functional outcomes following pars plana vitrectomy (PPV) for traumatic macular hole (TMH), investigate optical coherence tomography (OCT)-based prognostic factors, and compare outcomes between flap-based and non-flap internal limiting membrane (ILM) techniques. Methods: This retrospective consecutive case series included 33 eyes of 33 patients undergoing PPV for TMH between January 2017 and June 2024 at a tertiary referral center. Preoperative spectral-domain OCT parameters, including minimum linear diameter (MLD), basal diameter (BD), hole height (HH), intraretinal cysts, subretinal fluid, epiretinal membrane, and ellipsoid zone disruption, were evaluated. Anatomical closure and postoperative best-corrected visual acuity (BCVA) outcomes were analyzed. Results: The mean patient age was 28.7 ± 15.0 years, and blunt trauma accounted for 87.9% of cases. Median trauma-to-surgery interval was 10 weeks (IQR: 4–24 weeks). Mean BCVA improved significantly from 1.34 ± 0.54 logMAR preoperatively to 0.95 ± 0.59 logMAR postoperatively (p = 0.004). Single-surgery anatomical closure was achieved in 28 of 33 eyes (84.8%). Larger MLD and BD were significantly associated with poorer final BCVA, whereas greater HH was associated with successful anatomical closure. Flap-assisted techniques achieved higher closure rates compared with conventional ILM peeling (95.8% vs. 55.6%, p = 0.013). Conclusions: PPV for TMH was associated with favorable anatomical and functional outcomes. Larger hole dimensions were associated with poorer visual prognosis, whereas greater HH was associated with anatomical closure. Flap-assisted ILM techniques may improve anatomical success in TMH surgery.
S. Ozcalıskan, M. Ozbek, Anıl Korkmaz et al.· Journal of Clinical Medicine· 0 citations
Purpose: We evaluated the effect of internal limiting membrane (ILM) flap size on anatomical and functional outcomes of macular hole surgery, to determine the optimal flap size according to hole size.Methods: This retrospective study included 145 patients (147 eyes) with idiopathic full-thickness macular holes who underwent pars plana vitrectomy with ILM flap covering, followed for ≥6 months between January 2015 and August 2025 at a single center. Macular holes were classified as medium (250–400 μm) or large (400–800 μm) by minimum linear diameter. Patients were categorized by flap size into a standard group (≤1.5 disc diameters [DD]) and an extended group (>1.5–3 DD). Postoperative best-corrected visual acuity (BCVA), closure rate, foveal contour (U-, V-, or W-type), restoration of the external limiting membrane and ellipsoid zone, and complications were compared at 1 and 6 months.Results: In medium holes, both groups achieved 100% closure and comparable visual improvement, with no significant between- group differences. In large holes, the extended flap group showed greater BCVA improvement (ΔBCVA at 6 months, 0.49 vs. 0.12), higher closure rate (94.0% vs. 86.8%), more U-shaped foveal contours (48.0% vs. 13.2%), and higher external limiting membrane restoration (56.0% vs. 15.8%) than the standard group (p < 0.05). Multivariable analysis identified extended flap as an independent predictor of closure (adjusted OR, 6.77; 95% CI, 1.49–30.79; p = 0.013) and external limiting membrane restoration (adjusted OR, 10.42; 95% CI, 2.77–39.15; p = 0.001).Conclusions: In large macular holes, an extended ILM flap of approximately 1.5–3 DD improved anatomical stability and visual recovery, representing an effective surgical strategy. In medium holes, the standard flap achieved comparable outcomes, suggesting flap size modification may not be necessary for optimal results.
Na Gyung Kim, Myung In Yeom, Jung Min Park· Journal of the Korean Ophtha...· 0 citations
Objective: To investigate the clinical and surgical factors affecting visual outcomes and recurrence rates following pars plana vitrectomy (PPV) for rhegmatogenous retinal detachment (RRD). Methods: This retrospective study included 226 patients who underwent PPV for RRD between 2022 and 2024 at a tertiary care center in Türkiye. Demographic data, duration of symptoms, macular status, presence of proliferative vitreoretinopathy (PVR), type of intravitreal tamponade, pre-and postoperative best-corrected visual acuity (BCVA), intraocular pressure (IOP), and recurrence rates were analyzed. Results: Patients had a mean age of 57.9±14.4 years and were predominantly male (67.7%); 76.5% were macula-off, and 25.7% had PVR. Mean BCVA improved significantly from 1.8±0.7 to 1.0±0.6 logMAR (p<0.001), with preoperative BCVA independently predicting postoperative BCVA ( β =0.185, p=0.003). Visual improvement was poorer in eyes with macula-off status (p=0.044) and preoperative PVR (p=0.046), better with earlier surgical intervention (<7 days; p=0.030), and greater with C3F8 tamponade than with other agents (p=0.043), while combined cataract surgery did not influence outcomes (p=0.917). IOP increased modestly from 13.9±3.9 to 15.3±3.9 mmHg (p<0.001); 17.3% of patients required antiglaucoma-tous therapy, more often with silicone oil (SO) tamponade (p=0.023), without affecting final BCVA (p=0.917). Recurrent RRD occurred in 18.6% of patients and was higher in those with PVR (39.7% vs. 11.3%; p<0.01). Multivariable analysis identified PVR as the only independent predictor of recurrence (OR=3.44, p=0.023), and recurrence was lower with C3F8 than with SO (11.1% vs. 24.1%; p=0.026). Conclusion: These findings underscore the importance of preserving macular attachment, minimizing surgical delay, and recognizing PVR as a key determinant of both functional recovery and recurrence in optimizing outcomes after PPV for RRD. ABSTRACT
Güzide Akçay, U. Kıvrak, I. Karagöz et al.· Southern Clinics of Istanbul...· 0 citations
Objective: Idiopathic epiretinal membrane (ERM) is a fibroglial proliferation on the retinal surface that distorts the macular contour and impairs visual acuity. Restoration of the foveal pit following pars plana vitrectomy (PPV) is considered a key determinant of postoperative outcomes. This study aimed to evaluate the relationship between macular contour recovery and functional improvement after ERM surgery. Material and Methods: This retrospective study included 168 eyes of 155 patients who underwent PPV for idiopathic ERM between January 2009 and January 2011. Patients were grouped according to pre-and postoperative macular contour (MC) as regular or irregular. Best-corrected visual acuity (BCVA) and central macular thickness (CMT) were measured using the Snellen chart and spectral-domain optical coherence tomography (SD-OCT) before and 6 months after surgery. Statistical analyses were performed using paired t-tests, ANOVA, and Tukey’s post hoc tests (p<0.05). Results: The mean age differed significantly among groups (p=0.03). Preoperative BCVA was higher in patients with regular MC (0.37±0.23) than in those with irregular MC (0.16±0.11; p=0.02). Postoperative BCVA improved significantly in all groups (p=0.01). The greatest CMT reduction occurred in patients whose MC normalized postoperatively (CMT=-338.9±159.2 µm; p=0.01), indicating concordant structural and visual recovery. Conclusion: PPV for idiopathic ERM provides significant visual and anatomical improvement. Postoperative restoration of the foveal pit is strongly associated with superior BCVA gain and CMT reduction, highlighting foveal morphology as a key prognostic marker for surgical success
Aydın Maçin, Didem Serin· Zeynep Kamil Medical Journal· 0 citations
AIM
Idiopathic macular epiretinal membrane (iERM) induces traction and deformation of the macular retina, significantly impairing function and quality of life. This study aimed to evaluate the predictive value of early postoperative optical coherence tomography (OCT) microstructural changes for visual prognosis in patients undergoing vitrectomy with membrane peeling for iERM.
METHODS
A total of 110 patients diagnosed with iERM at Huzhou Aier Eye Hospital between January 2021 and July 2024 were retrospectively enrolled. According to OCT findings, patients were divided into stage I (n = 38), stage II (n = 52), and stage III (n = 20). All patients underwent 23-gauge minimally invasive vitrectomy combined with indocyanine green staining and peeling of the epiretinal membrane and internal limiting membrane. Best-corrected visual acuity (BCVA), central macular thickness (CMT), subfoveal choroidal thickness (SFCT), choroidal thickness at 1000 μm from the nasal side of the macular fovea (NFCT), and choroidal thickness at 1000 μm from the temporal side of the macular fovea (TFCT) were assessed before surgery and at 1 and 3 months postoperatively. Repeated-measures analysis of variance was used to compare intergroup differences over time, and multivariate logistic regression was performed to identify indicators associated with a favorable visual prognosis.
RESULTS
Significant gradient differences were observed among the three groups in CMT, SFCT, NFCT, TFCT, and BCVA, with stage I patients exhibiting significantly lower values than those in stage II and stage III (all p < 0.05). During postoperative follow-up, OCT parameters and visual acuity improved in all groups, with significantly greater improvement in stage I patients compared with stage II or stage III (all p < 0.05). Repeated-measures analysis demonstrated a significant time × group interaction effect for CMT (F = 2.334, p = 0.032), with a greater rate of CMT reduction in stage I patients. At 6 months postoperatively, 71 patients (64.55%) achieved a favorable visual prognosis. Multivariate logistic regression analysis indicated that lower CMT at 1 month postoperatively (OR = 0.98, 95% CI: 0.97-0.99, p < 0.05) was significantly associated with favorable visual outcomes at 6 months.
CONCLUSIONS
Postoperative anatomical and functional recovery in iERM patients is stage-dependent. Lower CMT at 1 month after surgery is significantly associated with favorable visual outcomes at 6 months, suggesting its potential value as an early postoperative prognostic indicator. These findings underscore the importance of incorporating early postoperative OCT assessment into clinical follow-up to facilitate individualized prognosis and patient counseling.