Explainable multimodal AI and neuro-symbolic clinical decision support system for chronic eye disease management: a digital health implementation study - Report - MDSpire

Explainable multimodal AI and neuro-symbolic clinical decision support system for chronic eye disease management: a digital health implementation study

  • By

  • Mini Han Wang

  • Simon Ming Yuen Lee

  • Guanghui Hou

  • Yapeng Wang

  • José C. Alves

  • Ruitao Xie

  • Yaqing He

  • Jin Liu

  • Xiaoxiao Fang

  • Yu Yang

  • Xiaodong Cai

  • Shuai Zheng

  • Ziyang Yu

  • Ethan Zhiyuan Lin

  • Chonin Cheang

  • Kuok Kai Ian

  • Shuai Qin

  • July 9, 2026

  • 0 min

Share

Clinical Report: AI and Neuro-Symbolic Approach in AMD Management

Overview

This study evaluates an AI-based system for automating administrative documentation in age-related macular degeneration (AMD) care, achieving high accuracy in information extraction.

Background

Chronic diseases like age-related macular degeneration (AMD) impose substantial administrative burdens that contribute to healthcare costs and clinician burnout. The integration of AI technologies in clinical workflows aims to alleviate these burdens.

Data Highlights

MetricValue
Clinical entity extraction accuracy98.3%
Administrative information extraction accuracy96.7%
Documentation time per encounter3.2 ± 1.1 min
Reduction in documentation time88%
Estimated labor cost saving per visit52 CNY (≈7 USD)
Projected annual savings per AMD patient42–56 USD

Key Findings

  • The AI system achieved 100% reimbursement compliance with no denied claims.
  • Mean documentation time decreased from 25.0 ± 5.0 min to 3.2 ± 1.1 min.
  • Labor cost savings were approximately 52 CNY (≈7 USD) per visit.
  • The framework integrates neuro-symbolic reasoning with large language models for administrative automation.

Clinical Implications

The implementation of AI-driven administrative automation can significantly reduce the time clinicians spend on documentation.

Conclusion

The study demonstrates that AI-enabled administrative automation can enhance operational efficiency and reduce costs in AMD care.

Related Resources & Content

  1. American Academy of Ophthalmology, Age-Related Macular Degeneration Preferred Practice Pattern, 2024 -- Comprehensive guidance on AMD diagnosis and management.
  2. American Diabetes Association, Standards of Care in Diabetes—2026, 2026 -- Current U.S. guidance for retinopathy screening.
  3. Cochrane, Comparative efficacy of intravitreal anti-VEGF therapy for neovascular age-related macular degeneration, 2026 -- Network meta-analysis on AMD treatment.
  4. Journal of Medical Internet Research (JMIR) — Operationalizing Digital Health Equity in Artificial Intelligence–Enabled Patient Decision Aids for Older Adults: Mixed Methods Study
  5. the ophthalmologist — Synthetic Data, Real Diagnostic Gains
  6. Retinal Physician — AI-READI: A Multimodal Data Set for Diabetic Eye Research
  7. npj Digital Medicine — Evaluating the Real-World Application of Deep Learning Technologies in Healthcare: A Systematic Review Based on Implementation Science Principles
  8. Operationalizing Digital Health Equity in AI-Enabled Patient Decision Aids
  9. Synthetic Data, Real Diagnostic Gains
  10. AI-READI: A Multimodal Data Set for Diabetic Eye Research
  11. Age-Related Macular Degeneration Preferred Practice Pattern® - Ophthalmology
  12. The American Diabetes Association Releases “Standards of Care in Diabetes—2026” | American Diabetes Association
  13. The March to Harmonized Imaging Standards for Retinal Imaging - PMC
  14. Anti‐vascular endothelial growth factor (anti‐VEGF) agents for neovascular age‐related macular degeneration (nAMD): a network meta‐analysis - PMC
  15. Comparative efficacy of intravitreal anti‐VEGF therapy for neovascular age‐related macular degeneration: A systematic review with network meta‐analysis - PMC
  16. Baseline OCT Biomarkers Predicting Visual Outcomes in Neovascular Age-Related Macular Degeneration - Ophthalmology
  17. Aflibercept 8 mg treat-and-extend pathway for the treatment of neovascular age-related macular degeneration: guidance from a UK expert panel | Eye
  18. Clinical setting-dependent diagnostic accuracy of artificial intelligence and store-and-forward diabetic retinopathy screening: a systematic review and meta-analysis | npj Digital Medicine
  19. Frontiers | Effectiveness of screening modalities for early detection of diabetic retinopathy: a systematic review and meta-analysis of tele-ophthalmology, AI-based tools, and conventional methods

Original Source(s)

Explainable multimodal AI and neuro-symbolic clinical decision support system for chronic eye disease management: a digital health implementation study

  • by Mini Han Wang, Simon Ming Yuen Lee, Guanghui Hou, Yapeng Wang, José C. Alves, Ruitao Xie, Yaqing He, Jin Liu, Xiaoxiao Fang, Yu Yang, Xiaodong Cai, Shuai Zheng, Ziyang Yu, Ethan Zhiyuan Lin, Chonin Cheang, Kuok Kai Ian, Shuai Qin

  • July 9, 2026

Related Content

Visual outcomes of sight threatening radiation-induced meningiomas after low-dose head irradiation: tinea capitis as a paradigm

Case Report: Multiple sclerosis and Neurofibromatosis type 1: a rare comorbidity

The Gut–Eye Cataract Connection

Multiomics study reveals reduced anti-inflammatory gut metabolites and altered bacterial populations in patients with age-related cataract

  • July 9, 2026

  • 3 min