Dynamic Structural Recovery Parameters Enhance Prediction of Visual Outcomes After Macular Hole Surgery

2025-09-11

AI Summary

Current predictive models for postoperative visual acuity recovery in idiopathic full-thickness macular hole (iFTMH) exhibit insufficient accuracy. Method: This study introduces, for the first time, “dynamic structural recovery parameters” and proposes a multimodal deep learning framework that fully automates prediction by integrating volumetric optical coherence tomography (OCT) data, quantitative morphological features, and qualitative clinical indicators. Technically, it employs a stage-specific OCT segmentation network (Dice > 0.89) and an end-to-end feature extraction pipeline, synergistically combining binary logistic regression with a multimodal fusion architecture. Results: Across all follow-up time points, the model achieves up to a 0.12 improvement in AUC over conventional regression methods, significantly enhancing discriminative capability for postoperative visual prognosis and demonstrating tangible clinical utility for decision support.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Purpose: To introduce novel dynamic structural parameters and evaluate their integration within a multimodal deep learning (DL) framework for predicting postoperative visual recovery in idiopathic full-thickness macular hole (iFTMH) patients. Methods: We utilized a publicly available longitudinal OCT dataset at five stages (preoperative, 2 weeks, 3 months, 6 months, and 12 months). A stage specific segmentation model delineated related structures, and an automated pipeline extracted quantitative, composite, qualitative, and dynamic features. Binary logistic regression models, constructed with and without dynamic parameters, assessed their incremental predictive value for best-corrected visual acuity (BCVA). A multimodal DL model combining clinical variables, OCT-derived features, and raw OCT images was developed and benchmarked against regression models. Results: The segmentation model achieved high accuracy across all timepoints (mean Dice > 0.89). Univariate and multivariate analyses identified base diameter, ellipsoid zone integrity, and macular hole area as significant BCVA predictors (P < 0.05). Incorporating dynamic recovery rates consistently improved logistic regression AUC, especially at the 3-month follow-up. The multimodal DL model outperformed logistic regression, yielding higher AUCs and overall accuracy at each stage. The difference is as high as 0.12, demonstrating the complementary value of raw image volume and dynamic parameters. Conclusions: Integrating dynamic parameters into the multimodal DL model significantly enhances the accuracy of predictions. This fully automated process therefore represents a promising clinical decision support tool for personalized postoperative management in macular hole surgery.

Problem

• Predicting visual recovery after macular hole surgery using dynamic parameters
• Integrating multimodal deep learning with OCT-derived structural features
• Enhancing postoperative outcome prediction through automated quantitative analysis

Innovation

• Multimodal deep learning model integration
• Dynamic structural recovery parameter extraction
• Automated OCT segmentation and feature pipeline