Scholarlink

Artificial intelligence (AI) and deep learning (DL)-based systems have gained significant attention in the diagnosis of ophthalmic diseases, including cataracts, glaucoma, diabetic retinopathy (DR), and age-related macular degeneration (AMD). This work proposes a multimodal system that integrates fundus images, patient demographics, and clinical pathology data, achieving a diagnostic accuracy of 98.78% and a treatment recommendation accuracy of 93.19%. The model employs EfficientNet-B0 for image feature extraction and dense layers for processing tabular clinical data. Comprehensive evaluations using confusion matrices and ROC analysis demonstrate robust performance. The proposed system provides clinicians with an objective, data-driven decision-support tool that enhances diagnostic precision and improves patient outcomes.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multimodal Machine Learning Architecture for Predictive Diagnosis and Treatment of Ophthalmic Diseases

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Asmaa Abdelmawgoud,
  • Andrea M. Tonello

摘要

Artificial intelligence (AI) and deep learning (DL)-based systems have gained significant attention in the diagnosis of ophthalmic diseases, including cataracts, glaucoma, diabetic retinopathy (DR), and age-related macular degeneration (AMD). This work proposes a multimodal system that integrates fundus images, patient demographics, and clinical pathology data, achieving a diagnostic accuracy of 98.78% and a treatment recommendation accuracy of 93.19%. The model employs EfficientNet-B0 for image feature extraction and dense layers for processing tabular clinical data. Comprehensive evaluations using confusion matrices and ROC analysis demonstrate robust performance. The proposed system provides clinicians with an objective, data-driven decision-support tool that enhances diagnostic precision and improves patient outcomes.