Not provided
| ID | Type | Description | Link |
|---|---|---|---|
| MOH-OFLCG21jun-0003 | Other Grant/Funding Number | National Medical Research Council- Large Collaborative Grant |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Class |
|---|---|
| Singapore General Hospital | OTHER |
| SingHealth Polyclinics | OTHER |
Not provided
Not provided
Not provided
Not provided
Glaucoma is major cause of irreversible blindness and is characterized by optic nerve damage and visual field loss. Screening for glaucoma is challenging due to lack of a simple, accurate, cost-efficient and standardized process. Artificial intelligence, (AI) especially deep learning (DL) algorithms have potential to automate glaucoma detection, but have to be evaluated in real world settings, before public deployment. This study aims to evaluate the screening accuracy of a DL algorithm for glaucoma detection using colour fundus photographs (CFP) in a pragmatic randomised control trial (RCT). The algorithm will be tested in 1040 eligible patients with diabetes, recruited from the Diabetes & Metabolism Centre's clinics under the Singapore Integrated Diabetic Retinopathy Program (SiDRP) and randomized to 2 arms: AI-assisted model vs current standard of care (grader assessment). The performance of both arms will be compared to performance of study ophthalmologist in diagnosing glaucoma. We hypothesize that the DL model has better screening performance in detecting glaucoma in the community, compared to the current practice method.
Background: Glaucoma is the leading cause of irreversible blindness worldwide, characterized by optic nerve damage and visual field loss. Screening for glaucoma remains challenging due to lack of a simple, standardized, and cost-effective test. Artificial intelligence (AI), especially deep learning (DL), offers potential to improve and standardize glaucoma detection. However, its performance must be prospectively validated in real-world settings before public deployment.
Aim: To evaluate the accuracy and cost-effectiveness of a DL algorithm using colour fundus photographs (CFP) as a clinical decision support tool for glaucoma detection in a real-world setting.
Methods: A two-centre, single-blind, pragmatic randomized controlled trial (RCT) will be conducted among 1,040 adults with diabetes recruited from the Diabetes & Metabolism Centre (DMC) and SingHealth Polyclinics-Bukit Merah under the Singapore Integrated Diabetic Retinopathy Programme (SiDRP). After fundus imaging, participants will be randomized 1:1 to AI-assisted grading or current manual grading by graders at the SiDRP reading center (520 subjects per arm). Diagnostic performance will be compared against the gold-standard glaucoma diagnosis, determined via comprehensive ocular examination including intraocular pressure measurement, visual field testing, optical coherence tomography, and dilated fundus assessment. Cost-effectiveness will be evaluated using a cohort-based Markov model to estimate lifetime costs and incremental cost-effectiveness ratios (ICERs) of the two glaucoma screening strategies.
Clinical Significance: Integrating AI into glaucoma screening can address resource constraints and streamline detection. This study will provide real-world evidence on the accuracy and cost-effectiveness of AI-based screening. If validated, it could be integrated into national screening programs to enhance early detection, reduce unnecessary referrals, and prevent avoidable blindness through a cost-efficient, scalable approach.
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Artificial Intelligence Assisted Arm | Active Comparator | In this arm, human graders will review fundus photographs for glaucomatous features with the aid of output generated by an AI model trained to detect glaucoma. The AI output will be available during grading to support decision-making. |
|
| Current practice arm | Placebo Comparator | Graders will assess fundus photographs for glaucoma following standard clinical practice, using a pre-specified and established set of diagnostic criteria without access to AI-generated outputs. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Artificial Intelligence model to detect glaucoma | Diagnostic Test | A Vision Transformer model to detect glaucoma from fundus photos |
|
| Measure | Description | Time Frame |
|---|---|---|
| Evaluation of model performance | To compare the model performance in accuracy, sensitivity, specificity, positive predictive value and negative predictive value between the new AI-assisted clinical model and the current practice model in detecting glaucoma, with reference to the expert panel's standards. | At study completion (after all fundus images have been graded and data collection is finalized; approximately within 12 months of study initiation) |
| Measure | Description | Time Frame |
|---|---|---|
| Evaluation of time efficiency | To compare time efficiency between the AI-assisted clinical model and the current practice model, defined as the total time (in seconds) taken per participant for the entire screening process, from image access to final grading decision, recorded in real time during the grading session. | At study completion (after all fundus images have been graded and data collection is finalized; approximately within 12 months of study initiation) |
Not provided
Inclusion Criteria: We aim to recruit all eligible patients who attend Singapore General Hospital (SGH) Diabetes & Metabolism Centre's (DMC) clinics and SingHealth Polyclinics (SHP)-Bukit Merah under the Singapore Integrated Diabetic Retinopathy Programme (SiDRP). Patients are eligible for the study if
Exclusion Criteria: Patients meeting any of the exclusion criteria will be excluded from participation:
Patients who have difficulty in having retinal photos taken or have difficulties in completing the ocular examination protocols according to investigator's decision.
Any other contraindication(s) as indicated by the endocrinologists responsible for the patients.
-
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Role | Phone | Extension | |
|---|---|---|---|---|
| Ching-Yu Cheng, MD, PhD | Contact | 65767277 | chingyu.cheng@duke-nus.edu.sg | |
| Lavanya Raghavan, MD | Contact | 65767201 | raghavan.lavanya@seri.com.sg |
| Name | Affiliation | Role |
|---|---|---|
| Ching-Yu Cheng, MD, PhD | Singapore Eye Research Institute | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Singapore National Eye Centre | Recruiting | Singapore | Singapore | 168751 | Singapore |
For statistical analysis, for further refinement of the AI model
2028 onwards
Anonymised data only with the permission of the Principal Investigator
Not provided
Not provided
| ID | Term |
|---|---|
| D005901 | Glaucoma |
| ID | Term |
|---|---|
| D009798 | Ocular Hypertension |
| D005128 | Eye Diseases |
Not provided
Not provided
| ID | Term |
|---|---|
| D035061 | Control Groups |
| ID | Term |
|---|---|
| D015340 | Epidemiologic Research Design |
| D004812 | Epidemiologic Methods |
| D008919 | Investigative Techniques |
| D012107 | Research Design |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
|
| No intervention | Other | Control group with current practice model by human graders |
|
|
| Evaluation of Grader's Acceptance | To assess graders' acceptance and satisfaction with the AI-assisted clinical model compared to the current practice model in detecting glaucoma. Assessment will be conducted through brief in-task prompts during the grading process and through a structured post-study questionnaire. | At study completion (after all fundus images have been graded and data collection is finalized; approximately within 12 months of study initiation) |
| D008722 | Methods |