Prediction of long-term visual outcome of idiopathic full-thickness macular hole surgery using optical coherence tomography parameters that estimate potential preoperative photoreceptor damage

Prediction of Postoperative Macular Hole Status by Automated Preoperative Retinal OCT Analysis: A Narrative Review

Optical coherence tomography (OCT) is a non-invasive imaging modality essential for macular hole (MH) management. Artificial intelligence (AI) algorithms could be applied to OCT to garner insights for MH prognosis and outcomes. The objective was to review literature assessing automated image analysis algorithms in predicting postoperative outcomes for MH patients based on OCT images. A narrative search of all available published studies in peer-reviewed journals was conducted up to June 2023 following PRISMA guidelines. Three hundred sixty-eight publications underwent screening, with 14 selected for full-text review and seven determined as relevant. In MH status prediction, AI models achieved an area under the curve (AUC) of 83.6% to 98.4%. For postoperative visual acuity prediction, algorithm performance ranged from AUCs of 57% to 85%. In conclusion, novel AI algorithms were found to be predictive for postoperative MH status and postoperative visual acuity. More research in larger populations should be conducted to gauge the value of these novel algorithms in a real-world setting. [Ophthalmic Surg Lasers Imaging Retina 2025;56:XX-XX.].

Preoperative Optical Coherence Tomography Markers and Their Significance in the Treatment of Macular Holes Using the Inverted Internal Limiting Membrane Technique

Purpose The purpose of this study was to evaluate the short-term outcomes of pars plana vitrectomy (PPV) using the inverted flap technique for full-thickness macular hole (FTMH). Specifically, the study aimed to identify significant preoperative optical coherence tomography (OCT) parameters that can serve as predictors for postoperative distance and near best-corrected visual acuity (DBCVA and NBCVA). Methods A prospective analysis was conducted on patients diagnosed with FTMH who underwent PPV from September 2022 to November 2024 using the inverted flap technique. OCT imaging was conducted preoperatively and one month postoperatively. Parameters analyzed included base diameter (BD), height of the macular hole (HT), right arm length (RAL) of macular hole (MH), left arm length (LAL) of MH, macular hole index (MHI), diameter hole index (DHI), tractional hole index (THI), hole form factor (HFF) and central retinal subfield (CRS). Statistical analysis was conducted to calculate significant predictors for DBCVA and NBCVA short-term postoperative results after PPV, with statistical significance set at p<0.05. Results A total of 46 patients, 35 (76.1%) women and 11 (23.9%) men, aged 67.6±5.7 were included in the study. Means and standard deviation for analyzed parameters were BD=937.5±355 𝜇m, HD=424.6±188 𝜇m, HT=413.6±56.5 𝜇m, RAL=359.6±125.5 𝜇m, LAL=367.5±214 𝜇m, MHI=0.477±0.12, DHI=0.46±0.15, THI=1.2±0.71, HFF=0.79±0.17 and CRS=297.4±21.8 𝜇m. Twenty-four patients presented with large FTMH (≥400 µm), and twenty-two with small FTMH (<400 µm). All patients achieved full closure of the FTMH. The most common comorbidity was hypertension, with 13 patients (28.3%). The only statistically significant predictor of DBCVA change after surgery was MHI (p=0.01). Conclusions PPV surgery using the inverted flap technique has very high efficiency. MHI can be used in the prediction of postoperative DBCVA. Further research is needed to assess the role of THI and HFF as other predictors.

Supervised machine learning statistical models for visual outcome prediction in macular hole surgery: a single-surgeon, standardized surgery study

PURPOSE

To evaluate the predictive accuracy of various machine learning (ML) statistical models in forecasting postoperative visual acuity (VA) outcomes following macular hole (MH) surgery using preoperative optical coherence tomography (OCT) parameters.

METHODS

This retrospective study included 158 eyes (151 patients) with full-thickness MHs treated between 2017 and 2023 by the same surgeon and using the same intraoperative surgical technique. Data from electronic medical records and OCT scans were extracted, with OCT-derived qualitative and quantitative MH characteristics recorded. Six supervised ML models-ANCOVA, Random Forest (RF) regression, K-Nearest Neighbor, Support Vector Machine, Extreme Gradient Boosting, and Lasso regression-were trained using an 80:20 training-to-testing split. Model performance was evaluated on an independent testing dataset using the XLSTAT software. In total, the ML statistical models were trained and tested on 14,652 OCT data points from 1332 OCT images.

RESULTS

Overall, 91% achieved MH closure post-surgery, with a median VA gain of -0.3 logMAR units. The RF regression model outperformed other ML models, achieving the lowest mean square error (MSE = 0.038) on internal validation. The most significant predictors of VA were postoperative MH closure status (variable importance = 43.078) and MH area index (21.328). The model accurately predicted the post-operative VA within 0.1, 0.2 and 0.3 logMAR units in 61%, 78%, and 87% of OCT images, respectively.

CONCLUSION

The RF regression model demonstrated superior predictive accuracy for forecasting postoperative VA, suggesting ML-driven approaches may improve surgical planning and patient counselling by providing reliable insights into expected visual outcomes based on pre-operative OCT features.

CLINICAL TRIAL REGISTRATION NUMBER

Not applicable.

Predicting macular hole surgery outcomes: Integrating preoperative OCT features with supervised machine learning statistical models

PURPOSE

To evaluate various supervised machine learning (ML) statistical models to predict anatomical outcomes after macular hole (MH) surgery using preoperative optical coherence tomography (OCT) features.

METHODS

This retrospective study analyzed OCT data from idiopathic MH eyes at baseline and at 1-month post-surgery. The dataset was split 80:20 between training and testing. XLSTAT® statistical software (Lumivero, USA) was used to train different ML models on 10°CT parameters: prefoveal posterior cortical vitreous status, epiretinal membrane, intraretinal cysts, foveal retinal pigment epithelium hyperreflectivity, MH basal diameter, MH area (MHA), hole-forming factor, MH index, tractional hole index, and diameter hole index. The most effective statistical model was identified and was further assessed for accuracy, sensitivity, and specificity on a separate testing dataset.

RESULTS

Six ML statistical models were trained on 33,260°CT data points from 3326°CT images of 308 operated MH (300 patients) eyes. Following training and internal validation, the random forest (RF) model achieved the highest accuracy (0.92), precision (0.94), recall (0.97), and F-score (0.96), and lowest misclassification rate. RF model identified the MHA index as the best predictor of post-surgical anatomical success. Following external testing, the RF model confirmed the highest accuracy and lowest misclassification rate (8.8%).

CONCLUSION

ML-based statistical models can be used to predict MH status after surgery. The RF model was the most accurate ML model, and the MHA index was the best predictor of postoperative hole closure after surgery based on preoperative OCT parameters. These predictions may help with future surgical planning for MH patients.

Machine Learning and Optical-Coherence-Tomography-Derived Radiomics Analysis to Predict the Postoperative Anatomical Outcome of Full-Thickness Macular Hole

Full-thickness macular hole (FTMH) leads to central vision loss. It is essential to identify patients with FTMH at high risk of postoperative failure accurately to achieve anatomical closure. This study aimed to construct a predictive model for the anatomical outcome of FTMH after surgery. A retrospective study was performed, analyzing 200 eyes from 197 patients diagnosed with FTMH. Radiomics features were extracted from optical coherence tomography (OCT) images. Logistic regression, support vector machine (SVM), and backpropagation neural network (BPNN) classifiers were trained and evaluated. Decision curve analysis and survival analysis were performed to assess the clinical implications. Sensitivity, specificity, F1 score, and area under the receiver operating characteristic curve (AUC) were calculated to assess the model effectiveness. In the training set, the AUC values were 0.998, 0.988, and 0.995, respectively. In the test set, the AUC values were 0.941, 0.943, and 0.968, respectively. The OCT-omics scores were significantly higher in the "Open" group than in the "Closed" group and were positively correlated with the minimum diameter (MIN) and base diameter (BASE) of FTMH. Therefore, in this study, we developed a model with robust discriminative ability to predict the postoperative anatomical outcome of FTMH.