Retinal Clinical Assessment With AI-derived Quantitative Information

Inclusion criteria

Clinician Participants (Report Writers)

• Board-certified ophthalmologists or ophthalmology trainees (registrars or fellows) with clinical experience in interpreting fundus images.
• Capable of independently completing retinal clinical reports based on fundus photography.
• Willing and able to participate in the study tasks (report writing) under assigned study conditions.
• Able to provide informed consent.

Expert Evaluators (Outcome Assessors)

• Senior ophthalmologists with at least 5 years of post-certification clinical experience.
• Not involved in the report-writing stage of the study.
• Willing to evaluate de-identified reports across predefined quality dimensions.
• Able to provide informed consent.

Fundus Images (Data Inputs)

• Retinal fundus photographs of sufficient quality for clinical interpretation.
• Images representing a range of common retinal findings (normal or abnormal).
• Previously collected, de-identified images with no patient-identifiable information.

Exclusion criteria

Clinician Participants

• Lack of experience in interpreting fundus images (e.g., interns, medical students).
• Prior involvement in the development, training, or validation of the AI system being tested.
• Inability to complete reporting tasks due to time constraints or technical limitations.
• Any condition that may interfere with ability to perform study tasks (e.g., prolonged absence).

Expert Evaluators

• Participation in the intervention or control reporting arms.
• Prior exposure to or involvement in development of the AI system.
• Any conflict of interest affecting impartiality of report quality evaluation.

Fundus Images

• Poor-quality images with insufficient clarity for interpretation.
• Images containing artifacts or cropping that prevent accurate segmentation or assessment.
• Images with any remaining patient identifiers (excluded to maintain confidentiality).