Retinal DiseaseNCT07651943
AI-Assisted Interpretation of Ultra-Widefield Retinal Images
An observational study of Retinal Disease, run by Xiamen Ophthalmology Center Affiliated to Xiamen University at 5 sites in China.
Trial summary
The goal of this prospective observational study is to evaluate the impact of artificial intelligence (AI) assistance on clinician interpretation of ultra-widefield (UWF) retinal images. Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Retinal Disease
- What is being tested?
- AI-Assisted Interpretation and Unaided Interpretation
- Type of treatment
- Medical device
- How many people
- 462 participants
- Where
- 5 sitesChina
- Study dates
- 1 Jan 2026to 10 Feb 2026
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Study population: Participants undergoing clinically indicated ultra-widefield retinal imaging at participating ophthalmic centers in China, including individuals with diverse retinal diseases and retinal findings encountered in real-world clinical practice.
Who may be able to join
- Participants undergoing ultra-widefield retinal imaging at participating ophthalmic centers;
Who cannot join
- Poor-quality or ungradable retinal images;
Trial locations and contacts
5 sites in 1 country.
5 sites in 1 country
China5 sites
Chongqing Huaxia Eye Hospital
Chongqing, Chongqing Municipality
Fuzhou Eye Hospital
Fuzhou, Fujian, 361000
Hengshui Tongrui Eye Hospital
Hengshui, Hebei
Heze Huaxia Eye Hospital
Heze, Shandong
Xiamen Eye Center of Xiamen University
Xiamen, Fujian, 361000
About this study
Official title: Prospective Multi-Center Evaluation of AI-Assisted Interpretation of Ultra-Widefield Retinal Images in a Multi-Reader Crossover Study
The goal of this prospective observational study is to evaluate the impact of artificial intelligence (AI) assistance on clinician interpretation of ultra-widefield (UWF) retinal images.
The main questions it aims to answer are:
Read more
whether AI assistance improves the diagnostic performance of ophthalmologists in detecting retinal findings on UWF retinal images; whether AI assistance improves sensitivity, specificity, and inter-reader agreement across clinicians with different levels of experience.
Approximately 600 UWF retinal images prospectively collected from multiple ophthalmic centers in China will be included. Images will be independently annotated by expert retinal specialists to establish reference labels for retinal finding categories.
Four ophthalmologists with different levels of clinical experience, including one senior retinal specialist and three junior ophthalmologists, will participate in a crossover multi-reader study.
For each clinician, the dataset will be randomly divided into two equal subsets. During the first reading session, clinicians will evaluate one subset without AI assistance and the other subset with AI assistance. After a washout interval of at least two weeks, the reading conditions will be reversed in a second reading session with independently randomized image order.
Under the AI-assisted condition, clinicians will be provided with category-level AI prediction probabilities for retinal findings. No localization maps, heatmaps, segmentation overlays, or automated diagnostic recommendations will be displayed. Clinicians will retain full autonomy over final decisions.
Reader performance under AI-assisted and unaided conditions will be compared using expert reference annotations as the ground truth.
Read the detailed description
This study is a prospective multi-center observational reader study designed to evaluate the impact of artificial intelligence (AI) assistance on clinician interpretation of ultra-widefield (UWF) retinal images.
Approximately 600 UWF retinal images will be prospectively collected from multiple ophthalmic centers in China. Images will be acquired using clinically routine UWF retinal imaging systems and will include a broad spectrum of retinal diseases and retinal findings encountered in real-world clinical practice.
All images will undergo independent expert annotation by retinal specialists to establish reference labels for retinal finding categories. These expert annotations will serve as the reference standard for subsequent performance evaluation.
Four ophthalmologists with different levels of clinical experience will participate in the reader study, including:
one senior retinal specialist with approximately five years of retinal clinical experience; three junior ophthalmologists with approximately two years of ophthalmology residency training.
A randomized crossover multi-reader design will be implemented to minimize recall bias and balance reading conditions.
For each clinician, the image dataset will be randomly divided into two equal subsets (subset A and subset B; approximately 300 images each).
During Round 1:
subset A will be interpreted without AI assistance; subset B will be interpreted with AI assistance.
After a washout interval of at least two weeks, the reading conditions will be reversed during Round 2:
subset A will be interpreted with AI assistance; subset B will be interpreted without AI assistance.
Image order will be independently randomized for each session and each clinician.
Under the unaided condition, clinicians will evaluate retinal images using standard clinical interpretation without AI output.
Under the AI-assisted condition, clinicians will receive category-level AI prediction probabilities for retinal finding categories. The AI output will provide probabilistic confidence scores only and will not include lesion localization maps, heatmaps, segmentation overlays, or automated binary recommendations.
Clinicians will remain blinded to the expert reference labels and to the interpretations of other readers. Final diagnostic decisions will be independently determined by each clinician.
The primary analysis will compare diagnostic performance between unaided and AI-assisted conditions, including sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and inter-reader agreement.
- Conditions
- Retinal Disease
- Being tested
- AI-Assisted Interpretation, Unaided Interpretation
- Keywords
- Artificial Intelligence, Ultra-Widefield Imaging, Retinal Imaging, Reader Study, Diagnostic Performance, AI-Assisted Diagnosis
- Medical subject headings
- Retinal Diseases
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-Assisted InterpretationDevice
Clinicians interpret ultra-widefield retinal images with access to AI-generated category-level prediction probabilities for retinal findings.
Unaided InterpretationDevice
Clinicians interpret ultra-widefield retinal images without AI assistance using routine retinal image interpretation alone.
| Study group | Role | What they receive |
|---|---|---|
| AI-Assisted Interpretation | Clinicians interpret ultra-widefield retinal images with access to AI-generated category-level prediction probabilities for retinal findings. Receives: Device: AI-Assisted Interpretation | |
| Unaided Interpretation | Clinicians interpret ultra-widefield retinal images without AI assistance using routine retinal image interpretation alone. Receives: Device: Unaided Interpretation |
What is being measured
The primary outcome is the main question the study is designed to answer.
Sensitivity for retinal finding detection
Sensitivity of clinicians in detecting retinal finding categories under AI-assisted and unaided conditions using expert annotations as the reference standard.
Measured: through study completion, an average of 2 months
Specificity for retinal finding detection
Specificity of clinicians in detecting retinal finding categories under AI-assisted and unaided conditions.
Measured: through study completion, an average of 2 months
Secondary outcomes (3)
Area under the receiver operating characteristic curve (AUC)
The AUC quantifies the overall ability to correctly distinguish the presence versus absence of predefined retinal findings on ultra-widefield retinal images. AUC values range from 0.5 (no discriminative ability) to 1.0 (perfect discrimination). Clinician interpretations will be compared with an expert-adjudicated reference standard under AI-assisted and unaided conditions.
Measured: through study completion, an average of 2 months
Inter-reader agreement
Agreement among participating clinicians in classifying predefined retinal findings on ultra-widefield retinal images. Agreement will be quantified using Cohen's kappa coefficient (for pairwise comparisons) or Fleiss' kappa coefficient (for multiple readers). Kappa values range from 0 (no agreement beyond chance) to 1 (perfect agreement).
Measured: At study completion (up to 3 months)
Diagnostic performance improvement among junior ophthalmologists
Improvement in diagnostic performance of junior ophthalmologists when interpreting ultra-widefield retinal images with AI assistance compared with unaided interpretation, measured by changes in sensitivity, specificity, accuracy, and AUC using the expert-adjudicated reference standard.
Measured: At study completion (up to 3 months)
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted16 Jun 2026
- Study start1 Jan 2026
- Primary completion1 Feb 2026
- Study completion10 Feb 2026
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Retinal DiseaseStudies of the same condition, open and under way.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Other
- Time perspective
- Prospective
- Enrolment
- 462 participants (actual)
Sponsor and investigators
- Lead sponsor
- Xiamen Ophthalmology Center Affiliated to Xiamen University
- Sponsor type
- University, hospital or other
- Responsible party
- Principal investigator, XiujuChen, Xiamen Ophthalmology Center Affiliated to Xiamen University
- Investigators
- Xiuju Chen, Principal investigator, Xiamen Eye Center of Xiamen University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07651943
- Sponsor's protocol ID
- XMYKZX-KY-2026-008
- Status last verified
- Jun 2026
- First submitted
- 5 Jun 2026
- Last updated
- 16 Jun 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- No: De-identified individual participant data underlying the results reported in this study, including retinal imaging data and associated annotations, may be made available upon reasonable request to the corresponding investigator following publication, subject to institutional ethics approval, data-sharing agreements, and applicable data governance and privacy regulations.
Study at a glance
From the registry record, last updated by the sponsor on 16 Jun 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Prospective Multi-Center Evaluation of AI-Assisted Interpretation of Ultra-Widefield Retinal Images in a Multi-Reader Crossover Study
- ClinicalTrials.gov ID
- NCT07651943
- Acronym / sponsor ID
- XMYKZX-KY-2026-008
- Conditions
- Retinal Disease
- Keywords
- Artificial Intelligence, Ultra-Widefield Imaging, Retinal Imaging, Reader Study, Diagnostic Performance, AI-Assisted Diagnosis
- Study type
- Observational
- Recruitment status
- Completed
- Enrolment
- 462 participants (actual)
- Lead sponsor
- Xiamen Ophthalmology Center Affiliated to Xiamen UniversityUniversity, hospital or other
- Study start
- 1 Jan 2026 (actual)
- Primary completion
- 1 Feb 2026 (actual)
- Study completion
- 10 Feb 2026 (actual)
- First posted
- 16 Jun 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
The goal of this prospective observational study is to evaluate the impact of artificial intelligence (AI) assistance on clinician interpretation of ultra-widefield (UWF) retinal images.
The main questions it aims to answer are:
whether AI assistance improves the diagnostic performance of ophthalmologists in detecting retinal findings on UWF retinal images; whether AI assistance improves sensitivity, specificity, and inter-reader agreement across clinicians with different levels of experience.
Approximately 600 UWF retinal images prospectively collected from multiple ophthalmic centers in China will be included. Images will be independently annotated by expert retinal specialists to establish reference labels for retinal finding categories.
Four ophthalmologists with different levels of clinical experience, including one senior retinal specialist and three junior ophthalmologists, will participate in a crossover multi-reader study.
For each clinician, the dataset will be randomly divided into two equal subsets. During the first reading session, clinicians will evaluate one subset without AI assistance and the other subset with AI assistance. After a washout interval of at least two weeks, the reading conditions will be reversed in a second reading session with independently randomized image order.
Under the AI-assisted condition, clinicians will be provided with category-level AI prediction probabilities for retinal findings. No localization maps, heatmaps, segmentation overlays, or automated diagnostic recommendations will be displayed. Clinicians will retain full autonomy over final decisions.
Reader performance under AI-assisted and unaided conditions will be compared using expert reference annotations as the ground truth.
Detailed description
This study is a prospective multi-center observational reader study designed to evaluate the impact of artificial intelligence (AI) assistance on clinician interpretation of ultra-widefield (UWF) retinal images.
Approximately 600 UWF retinal images will be prospectively collected from multiple ophthalmic centers in China. Images will be acquired using clinically routine UWF retinal imaging systems and will include a broad spectrum of retinal diseases and retinal findings encountered in real-world clinical practice.
All images will undergo independent expert annotation by retinal specialists to establish reference labels for retinal finding categories. These expert annotations will serve as the reference standard for subsequent performance evaluation.
Four ophthalmologists with different levels of clinical experience will participate in the reader study, including:
one senior retinal specialist with approximately five years of retinal clinical experience; three junior ophthalmologists with approximately two years of ophthalmology residency training.
A randomized crossover multi-reader design will be implemented to minimize recall bias and balance reading conditions.
For each clinician, the image dataset will be randomly divided into two equal subsets (subset A and subset B; approximately 300 images each).
During Round 1:
subset A will be interpreted without AI assistance; subset B will be interpreted with AI assistance.
After a washout interval of at least two weeks, the reading conditions will be reversed during Round 2:
subset A will be interpreted with AI assistance; subset B will be interpreted without AI assistance.
Image order will be independently randomized for each session and each clinician.
Under the unaided condition, clinicians will evaluate retinal images using standard clinical interpretation without AI output.
Under the AI-assisted condition, clinicians will receive category-level AI prediction probabilities for retinal finding categories. The AI output will provide probabilistic confidence scores only and will not include lesion localization maps, heatmaps, segmentation overlays, or automated binary recommendations.
Clinicians will remain blinded to the expert reference labels and to the interpretations of other readers. Final diagnostic decisions will be independently determined by each clinician.
The primary analysis will compare diagnostic performance between unaided and AI-assisted conditions, including sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and inter-reader agreement.
Study design
- Observational model
- Other
- Time perspective
- Prospective
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| AI-Assisted Interpretation | – | Device: AI-Assisted InterpretationClinicians interpret ultra-widefield retinal images with access to AI-generated category-level prediction probabilities for retinal findings. |
| Unaided Interpretation | – | Device: Unaided InterpretationClinicians interpret ultra-widefield retinal images without AI assistance using routine retinal image interpretation alone. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
- Study population
- Participants undergoing clinically indicated ultra-widefield retinal imaging at participating ophthalmic centers in China, including individuals with diverse retinal diseases and retinal findings encountered in real-world clinical practice.
Key inclusion criteria (1 listed)
- Participants undergoing ultra-widefield retinal imaging at participating ophthalmic centers;
Key exclusion criteria (1 listed)
- Poor-quality or ungradable retinal images;
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| AI-Assisted InterpretationClinicians interpret ultra-widefield retinal images with access to AI-generated category-level prediction probabilities for retinal findings. | Device | AI-Assisted Interpretation |
| Unaided InterpretationClinicians interpret ultra-widefield retinal images without AI assistance using routine retinal image interpretation alone. | Device | Unaided Interpretation |
Primary outcome
Sensitivity for retinal finding detection
Time frame: through study completion, an average of 2 months
Sensitivity of clinicians in detecting retinal finding categories under AI-assisted and unaided conditions using expert annotations as the reference standard.
Specificity for retinal finding detection
Time frame: through study completion, an average of 2 months
Specificity of clinicians in detecting retinal finding categories under AI-assisted and unaided conditions.
3 secondary outcomes
Area under the receiver operating characteristic curve (AUC)
Time frame: through study completion, an average of 2 months
Inter-reader agreement
Time frame: At study completion (up to 3 months)
Diagnostic performance improvement among junior ophthalmologists
Time frame: At study completion (up to 3 months)
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 16 Jun 2026.
- Individual participant dataSharing planned: No. De-identified individual participant data underlying the results reported in this study, including retinal imaging data and associated annotations, may be made available upon reasonable request to the corresponding investigator following publication, subject to institutional ethics approval, data-sharing agreements, and applicable data governance and privacy regulations.
Related trials for Retinal Disease
Recruiting
Implementing AI-based Glaucoma Screening Within Federally Qualified Health Centers
Glaucoma, Ocular Hypertension
RecruitingObservational study
Pivotal Trial of an Automated AI-based System for Early Diagnosis and Prediction of Late Age-related Macular Degeneration
Age-related Macular Degeneration (AMD)
Active, not recruitingObservational study
Real World Evidence in China: Faricimab Use in Diabetic Macular Edema, Retinal Vein Occlusion, and Neovascular Age-Related Macular Degeneration (The Farseeing Study)
Diabetic Macular Edema, Neovascular Age-related Macular Degeneration
Active, not recruitingObservational study
Retinal Pigment Epithelium Safety Study For Patients In B4711001
Age Related Macular Degeneration
Not yet recruitingObservational study
Efficacy of Aflibercept (8 mg) With Sequential Laser Photocoagulation for Macular Edema Secondary to Retinal Artery Macroaneurysm: Retrospective Study"
Retinal Arterial Macroaneurysm
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Xiuju Chen principal investigator
Xiamen Eye Center of Xiamen University
5 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Retinal Disease, run by Xiamen Ophthalmology Center Affiliated to Xiamen University at 5 sites in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 1 inclusion and 1 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 16 Jun 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 5 sites in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Sensitivity for retinal finding detection (time frame: through study completion, an average of 2 months). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 16 Jun 2026.