XQuick Search
AI-Based Visual Prognosis in Full-Thickness Macular Hole Surgery Using the ILM Flap Technique
Lukpan Nurlanovich Orazbekov1, Kairat Ruslanuly2, Elmira Gazizovna Kanafyanova3, Altynai Kairatkyzy Kairat41Department of First Ophthalmology, Kazakh Eye Research Institute, Almaty, Kazakhstan2Department of Science Management, First Ophthalmology Department, Kazakh Eye Research Institute, Almaty, Kazakhstan
3Department of Science Management, Kazakh Eye Research Institute, Almaty, Kazakhstan
4Department of Third Ophthalmology, Kazakh Eye Research Institute, Almaty, Kazakhstan
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 (r s=0.5885, p<0.001), with a moderate correlation at 12 months (r s=0.4156, p=0.005), a weak correlation preoperatively (r s=0.3029, p=0.043), and no significant correlation at 7 days (r s=0.1949, p=0.199).
DISCUSSION AND 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.
Keywords: Artificial intelligence, deep learning model, full-thickness macular hole, internal limiting membrane flap, multimodal large language model, visual prognosis
Manuscript Language: English
