Related Experiment Video
Updated: Oct 17, 2025
Intravitreous Injection for Establishing Ocular Diseases Model
Published on: October 1, 2007
A Proposed Framework for Machine Learning-Aided Triage in Public Specialty Ophthalmology Clinics in Hong Kong
Yalsin Yik Sum Li1, Varut Vardhanabhuti2, Efstratios Tsougenis3
1Department of Ophthalmology, Li Ka Shing Faculty of Medicine, The University of Hong Kong, 301B Cyberport 4, 100 Cyberport Road, Pokfulam, Hong Kong SAR, China.
Insights
This study proposes a machine learning (ML) framework to improve the efficiency of ophthalmic clinic referral triaging. The framework aims to reduce practitioner workload and enhance patient care in Hong Kong's public eye clinics.
Area of Science:
- Ophthalmology
- Medical Informatics
- Artificial Intelligence
Background:
- Public ophthalmic clinics in Hong Kong face high referral volumes, leading to significant practitioner workload.
- Healthcare worker shortages exacerbate the need for efficient triaging systems in these clinics.
- Existing medical artificial intelligence research lacks a specific framework for ophthalmology triage algorithms.
Purpose of the Study:
- To propose a general framework for developing, deploying, and evaluating machine learning (ML)-based triaging algorithms in clinical ophthalmology settings.
- To identify best practices for creating robust ML triage networks and establish protocols for their maintenance and impact assessment.
Main Methods:
- Conducted a comprehensive literature review to identify best practices in ML algorithm development for medical workflows.
- Defined protocols for the deployment, maintenance, and evaluation of ML-based triaging systems in a clinical environment.
- Focused on assessing clinical utility and external validity beyond laboratory settings.
Main Results:
- Identified key considerations and best practices for developing ML triaging algorithms in ophthalmology.
- Proposed a structured framework encompassing development, deployment, and evaluation phases.
- Highlighted the importance of maintenance protocols and impact assessment for clinical integration.
Conclusions:
- The proposed framework provides a foundation for accelerating pilot studies and deployment of ML-based triaging in ophthalmology.
- Implementing such a framework can potentially alleviate practitioner workload and improve patient and practitioner satisfaction.
- This initiative addresses the need for efficient solutions in resource-strained healthcare systems.
Abstract:
The public specialty ophthalmic clinics in Hong Kong, under the Hospital Authority, receive tens of thousands of referrals each year. Triaging these referrals incurs a significant workload for practitioners and the other clinical duties. It is well-established that Hong Kong is currently facing a shortage of healthcare workers. Thus a more efficient system in triaging will not only free up resources for better use but also improve the satisfaction of both practitioners and patients. Machine learning (ML) has been shown to improve the efficiency of various medical workflows, including triaging, by both reducing the workload and increasing accuracy in some cases. Despite a myriad of studies on medical artificial intelligence, there is no specific framework for a triaging algorithm in ophthalmology clinics. This study proposes a general framework for developing, deploying and evaluating an ML-based triaging algorithm in a clinical setting. Through literature review, this study identifies good practices in various facets of developing such a network and protocols for maintenance and evaluation of the impact concerning clinical utility and external validity out of the laboratory. We hope this framework, albeit not exhaustive, can act as a foundation to accelerate future pilot studies and deployments.
