Clinical Research Directory

A Multimodal AI Agent for Ophthalmic Clinical Decision Support

This study is a multicenter randomized controlled trial evaluating the effectiveness and safety of EyeAgent, a multimodal artificial intelligence (AI) agent designed to assist ophthalmologists in clinical decision-making. Participants will be recruited from ophthalmology clinics and hospitals in Hong Kong and mainland China. The AI agent acts as a digital co-pilot, analyzing patient images and clinical history to provide diagnostic and management recommendations. The trial aims to determine whether the use of the AI agent improves diagnostic accuracy, treatment decision-making performance, report generation, workflow efficiency, and user satisfaction compared to standard clinical practice.

Identification of Cellular Biomarkers of Rare Eye Diseases in Adults

The cornea is the outermost transparent 'window' of the eye allowing light to enter and serving as the first-line immune and mechanical barrier. It is a complex avascular tissue composed of cells, stem cells, nerves, and collagen layers organized in an exquisite manner to maintain its transparency and self-healing capacity. This delicately balanced interplay of corneal elements is disrupted in rare diseases of the cornea, resulting in non-healing wounds, corneal ulceration, inflammation, new vessel ingrowth (neovascularization), defective innervation, scarring, oedema and loss of transparency. For many Rare Eye Diseases (REDs), drug development has been relatively unsuccessful, delivering few to no new therapies. Current management is often prohibitively expensive, has low efficacy and leads to debilitating side effects. The RESTORE VISION project (https://restorevision-project.eu/) aims to improve eye health by using cutting-edge models for each rare disease to test novel and repurposed compounds (9 in total) and determine drug mechanisms of action, formulating compounds as safe eye drop suspensions, and performing several first-in-human trials of novel therapies. Thes drugs have solid preliminary data showing beneficial effects in restoring the cell physiology, immune, avascular, neural and signaling environment in the cornea. The current clinical study is part of Work package 2 within the RESTORE VISION EU grant agreement (''Validation of human drug targets of repurposed drugs and novel therapies'') and aims to ascertain the expression levels of genes and proteins and investigate pathways of interest in human tissue and fluid samples of REDs, that are targeted by the proposed experimental/repurposed substances. Therapeutic target gene and/or protein expression will be verified in human blood, tears and conjunctival cells collected from 7 RED patient groups. The RESTORE VISION Consortium know multiple putative genes and proteins involved in the REDs and/or affected by the drugs to be tested in RED models. These will be analyzed in patient samples from the 7 REDs to see if they are 1) expressed at all; 2) differ in expression between patient and control group and 3) are correlated with clinical endpoints and/or symptoms of REDs. The 7 REDs under investigation are briefly explained as follows: 1. AAK: genetic progressive limbal stem cell degeneration leading to corneal neovascularization, inflammation, recurrent erosions, chronic pain and vision loss. 2. OCP: autoimmune scarring of the conjunctiva leads to deficient wound healing, inflammation, scarring, blindness and pain. 3. EEC Syndrome: Ectodermal Dysplasia causes pathological corneal scarring and blindness. 4. NK: involves a corneal nerve deficit leading to reduction or loss of corneal sensitivity, impaired wound healing, corneal ulceration and loss of vision. 5. LSCD: acquired or hereditary stem cell deficiency inducing epithelial breakdown, neovascularization, scarring and inflammation leading to decreased vision, tearing and pain. 6. oGvHD: a severe side-effect of successful bone-marrow transplantation leads to painful and blinding ocular surface inflammation, neovascularization and delayed wound healing. 7. CN: in high-risk transplantation, pathologic inflammation, corneal blood and lymphatic vessels are key risk factors for high-risk corneal graft failure, leading to graft rejection and blindness.

An Extension Test of Whether to Use Oral Anti-anxiety Drugs (XANAX) When Patients Choose Second Eye Cataract Surgery After Unblinding, and Analyze Their Anxiety, Satisfaction and Pain Satisfaction

Phacoemulsification is one of the most used surgical methods for cataract surgery today, and the surgeries are under the anesthetic and sedative to make it comfortable and safe for patients. The most important issue is which method is the best for reducing the patient's anxiety, pain, and discomfort during surgery. Previous studies have analyzed the impact of intravenous injection of sedative on the quality of phacoemulsification surgery; however, the impact of oral anti-anxiety drugs (XANAX) on cataract surgery has not been intensively studied. Therefore, the purpose of this study is to investigate the impact of XANAX on satisfaction in cataract surgery. Oral sedation is more convenient and safer than intravenous sedation. Therefore, the investigators will further analyze whether patients using oral anti-anxiety drugs will have an improvement in the pain, anxiety, overall satisfaction, and side effects related to nausea and dizziness in the phacoemulsification surgery. This study will detailed record the patient's status in various aspects using questionnaire scales and scores. Through this research, the investigators will have the opportunity to comprehensively improve the surgical quality of cataract patients in a safe and convenient manner. The investigators plan to collect data from patients who participated in the study "Anxiety and surgery satisfaction for cataract patient with different state anxiety" (Research Ethics Committee Case No.: 202302067MINB) from October 2023 to August 2025, and plan to undergo phacoemulsification and intraocular lens implantation surgery in their second eye with local anesthetic at the Department of Ophthalmology, National Taiwan University Hospital. The sample size of 250 participants was determined based on the type of intervention, expected effect size, outcome variability, desired statistical significance, trial power, and experiences from similar studies. Vulnerable populations and those with any relevant contraindications will be excluded during the enrollment process. All medical records and surgical process data, including privacy-related information, will only be accessible to professional medical personnel for analysis. The focus of this study will be on intraoperative satisfaction, pain scores, relevant discomfort symptoms during the surgery, and postoperative anxiety assessment scales.

Optimizing the Ocular Surface With Systane COMPLETE in Patients With Dry Eye Planning for Cataract Surgery

Regular use of Systane COMPLETE in dry eye subjects before cataract surgery may optimize the ocular surface.

Optimizing the Ocular Surface With Systane COMPLETE Pre- and Post-operatively in Patients With Dry Eye Planning for Cataract Surgery: An Extension Study of Optimizing the Ocular Surface With Systane COMPLETE in Patients With Dry Eye Planning for Cataract Surgery

Compare the corneal astigmatism data before and after the use of Systane COMPLETE to evaluate its impact on predicting changes in postoperative residual astigmatism, as well as the effects of using or not using Systane COMPLETE on preoperative and postoperative Ocular Surface Disease Index (OSDI) scores and Non-Invasive Tear Break-Up Time (NITBUT).

Clinical Determinants and Adverse Reactions to Tropicamide/Phenylephrine in Hospitalized Patients.

To evaluate the association between clinical determinants and the occurrence of adverse drug reactions in hospitalized patients who received tropicamide/phenylephrine 8 mg/50 mg/mL. An ambispective, interventional, longitudinal study will be conducted to actively identify adverse reactions to tropicamide/phenylephrine 8 mg/50 mg/mL, as well as the clinical determinants that may predispose patients to the occurrence of an adverse drug reaction (ADR). Data will be collected through the administration of a questionnaire and measurement of vital signs prior to the administration of tropicamide/phenylephrine 8 mg/50 mg/mL, and subsequently at 5 minutes, 15 minutes, 30 minutes, 1 hour, 2 hours after administration, with the aim of establishing an association between these variables.

AI-Orchestrated Workflow Versus Consultant Ophthalmologist for Refractive Surgery and Keratoconus Diagnosis (AEYE Trial)

Background and Rationale: Laser vision correction procedures, such as LASIK (Laser-Assisted In Situ Keratomileusis), PRK (Photorefractive Keratectomy), and SMILE (Small Incision Lenticule Extraction), are highly effective but require careful preoperative screening to ensure safety. One of the most critical aspects of screening is identifying keratoconus and other corneal ectatic disorders-conditions that cause progressive thinning and bulging of the cornea, often contraindicating surgery. Early detection is essential to avoid vision-threatening complications. Despite advanced corneal imaging tools such as Scheimpflug tomography and anterior segment optical coherence tomography (AS-OCT), accurate diagnosis-particularly in borderline or early-stage cases-remains challenging and subject to variability in human interpretation. Artificial intelligence (AI) offers the potential to improve diagnostic precision, reduce oversight, and standardize surgical planning. Purpose of the Study: This study evaluates the performance of AEYE (Automated Evaluation for Your Eye), a multi-agent AI system designed to support ophthalmologists in diagnosing keratoconus and determining refractive surgery eligibility. AEYE simulates the clinical workflow of an anterior segment specialist by orchestrating three specialized agents: History \& Risk Agent: Reviews patient history and extracts risk factors. Imaging Agent: Analyzes corneal tomography, AS-OCT, and epithelial mapping scans. Surgical Decision Agent: Integrates all findings, assigns a diagnosis, and recommends appropriate treatment options, including surgical eligibility or corneal cross-linking (CXL). Study Design: The study includes 50 real-world patient cases, both retrospective (from 2020 onward) and prospective, who were evaluated for refractive surgery or keratoconus. Each case is analyzed independently by AEYE and a consultant ophthalmologist (blinded to AI output), using the same multimodal clinical and imaging data. Diagnostic accuracy, agreement in surgical recommendations, and workflow efficiency are assessed. Anticipated Impact: By comparing AI-derived decisions with expert clinical judgment, this study aims to validate whether structured AI workflows like AEYE can serve as reliable, safe, and explainable decision support tools. If successful, AEYE may offer a scalable solution to reduce diagnostic variability and enhance the safety and consistency of refractive surgery screening.