The next-gen ophthalmologist: a narrative review of robotics and artificial intelligence

Introduction

Advancements in artificial intelligence (AI) and robotic technologies are rapidly transforming ophthalmology, with significant implications for diagnostic accuracy, surgical precision, and access to care (1,2). AI applications have demonstrated considerable promise in image-based screening and diagnosis, while robotic platforms are increasingly enabling unprecedented levels of surgical stability and precision in ophthalmic procedures (3). However, the pace of technological innovation has outpaced the structured integration of these tools into ophthalmology training and clinical practice, creating challenges for the safe, effective, and equitable adoption of these tools (4).

Despite growing clinical implementation, AI in ophthalmology remains largely concentrated in diagnostic and screening contexts, with limited emphasis on comprehensive clinician training and broader clinical application (5,6). Although curricula addressing foundational AI concepts for ophthalmology trainees have been proposed, including machine learning principles and critical appraisal of AI-driven studies, their integration into formal training programmes remains inconsistent (5). Similarly, the expanding role of robotic-assisted ophthalmic surgery has not been matched by standardized educational frameworks that define competency development, pre-clinical training requirements, or simulation-based learning strategies (5).

Robotic surgical systems, such as the Da Vinci (Intuitive Surgical, Inc., Sunnydale, CA, USA) and Preceyes platforms (Carl Zeiss Meditec, AG; Jena, Germany) (7), have demonstrated enhanced precision, stability, and control in complex ophthalmic procedures, contributing to reduced complication rates and improved surgical outcomes (7). As with all advanced surgical innovations, particularly those involving robotics, structured pre-training using ocular models and simulation is essential to reduce the learning curves and optimise patient safety (2,7). However, guidance on how such training should be implemented and integrated into existing ophthalmology curricula remains fragmented (2).

Beyond the operating theatre, AI and robotic technologies are increasingly shaping teleophthalmology and remote consultation models. AI-enabled diagnostic tools embedded within telehealth platforms offer the potential to deliver accurate diagnoses and personalised care to patients in remote and underserved settings, addressing long-standing inequities in access to eye care (8). Preparing future ophthalmologists to work competently within these digitally enabled care models is therefore no longer optional but essential (9).

AI systems have achieved expert-level performance in the screening and diagnosis of major blinding diseases, with several validated for clinical use (6,10,11). Concurrently, robotic platforms have demonstrated the ability to exceed human manual precision in delicate ophthalmic procedures through tremor reduction and motion scaling, particularly in vitreoretinal surgery (7). The integration of AI into robotic systems further enhances surgical decision-making via real-time imaging and semi-autonomous control (7,8). However, current literature remains fragmented, with AI research largely focused on diagnostics and robotic studies emphasising technical feasibility, offering limited insight into their combined clinical integration (6,8,10). This gap highlights the need for systematic evaluation of AI-robotic systems in routine ophthalmic practice.

Against this backdrop, this narrative review explores the integration of robotic systems in ophthalmic surgeries and the application of AI in diagnostics and treatment planning. We discuss current technologies, their benefits, limitations and prospects, providing insights into how these innovations are shaping the future of eye care and ophthalmology education and training. We present this article in accordance with the Narrative Review reporting checklist (available at https://aes.amegroups.com/article/view/10.21037/aes-25-48/rc).

Methods

To address the research objective, we conducted a qualitative, comprehensive synthesis of existing literature on digital learning tools and resources in ophthalmic surgery training. With the assistance of a librarian from the Library and Information Service at the University of the Free State, sources were identified exploring the following databases: the EBSCOhost platform (Academic Search Ultimate, Africa-Wide Information, Applied Science & Technology Source Ultimate, CAB Abstracts with Full Text, CINAHL with Full Text, Communication & Mass Media Complete, Health Source, MEDLINE) and Scopus.

The search was limited to articles published from January 2019 to May 2025. The keywords and Boolean operators used to refine searches included “robotics in ophthalmology surgery”; “artificial intelligence (AI) in ophthalmology”; and “machine learning in ophthalmology”.

All articles in English and with abstracts available, regardless of type, were included in the search. The articles were imported into Rayyan (Rayyan Systems Inc.; Cambridge, MA, USA), a web and mobile application for systematic reviews (12). The authors carried out independent, duplicate searches. All abstracts were reviewed and potentially eligible articles were read in full. Quality was ensured by comparing the abstract to the inclusion criteria. The final list of studies that met the eligibility criteria was compared, and disagreements were resolved through discussion. The search strategy is summarised in Table 1.

A total of 413 articles were retrieved, 91 duplicates were removed, and 90 articles were read to identify key themes. All full-text articles were available through the searched sources. Both authors critically assessed the quality and relevance of the sources.

Key content, findings and discussion

Table 2 summarises the review findings, followed by a discussion of the findings.

The history of robotics in medicine

The application of robots in surgery has a history spanning over four decades, assisting physicians in various medical fields. The first robotic surgery was performed in 1985 with the PUMA 560 robotic arm for neurosurgical biopsies, and the first robot specifically designed to aid medical teams, PROBOT, was used for transurethral prostate resection in 1988 (3,9). The U.S. Food and Drug Administration (FDA) approved the first medical use of a robot in 1992 (9). Early robotic systems such as Zeus and Da Vinci were subsequently incorporated into surgical procedures at a remarkable pace (3,9). The fundamental purpose of robots is to provide labour-saving solutions that simplify human tasks. Modern robots are designed to perform functions that require extreme precision, consistency and the ability to operate in areas that pose specific challenges and surgical risks (3,9).

Evolution of robotics in ophthalmology

Early developments in ophthalmic robotics began with foundational research. Robotic eye surgery was first described in 1989 with the stereotaxical microtelemanipulator (SMOS), designed by Guerrouad and Vidal, which allowed six degrees of freedom for precise ocular movements (2). In the same year, another prototype using the Stewart-based platform was developed to measure retinal vessel pressure and extract blood for research (9). These initial prototypes aimed to assist in vitreoretinal surgery and enhance precision by eliminating inter-operator variability (3).

Over time, four main categories of robotic systems have emerged in vitreoretinal surgery research. Handheld robotic instruments with built-in tremor cancellation capabilities—such as Micron and the SMART OCT-based device—enable enhanced precision during delicate procedures (2,13). Hand-on-hand robotic systems involve shared control between the surgeon and the robot, where the instrument is held by both and the surgeon’s applied force guides motion while the robot filters out tremor. The Steady-Hand Eye Robot developed by Taylor et al. is a notable example (14). Tele-operated robotic systems allow surgeons to control robotic instruments remotely from a console, enhancing precision and reducing fatigue. The Intraocular Robotic Interventional Surgical System (IRISS), for instance, can perform complex, multi-step procedures such as continuous curvilinear capsulorrhexis (CCC) and full cataract surgeries (9). Lastly, magnetic guidance robotic systems employ external magnetic fields to manipulate intraocular microrobots for targeted interventions such as drug delivery or retinal vein cannulation (13).

The Da Vinci Surgical System was primarily used in other surgical specialties, including urology, gynaecology and laparoscopic surgery. It has been explored for ophthalmic procedures and trialled for procedures such as pterygium repair, corneal grafts, amniotic membrane transplantation, and simulated cataract and strabismus surgery (9). The Preceyes surgical system has achieved notable milestones, including first-in-human trials for high-precision vitreoretinal procedures, such as epiretinal and inner limiting membrane dissection, subretinal drug delivery and retinal vein cannulation. It has received European Conformity (CE; Conformité Européenne) certification and is now commercially available (2). Similarly, the Ophthalmic Surgical Robot (OmSR) has been designed to minimise fundus tissue damage by providing enhanced precision and stability in delicate tasks such as needle insertion and membrane peeling (15).

Challenges and future directions

Despite notable advancements, the widespread adoption of robotic systems in ophthalmology faces several obstacles. Physiological limitations remain a significant challenge, as intraocular surgery demands exceptional precision within a confined intraocular space, complicating the adaptation of existing robotic platforms (16). Incorporating robotics into ophthalmology presents a substantial initial financial challenge for healthcare institutions, although it has the potential for long-term cost reductions (3,9,17). Limited availability of robotic systems, with the need for extensive staff training, including a steep learning curve for surgeons, are significant barriers. However, specialised training modules and virtual reality surgical training systems such as the Eyesi surgical simulator offer promising solutions to address these training gaps (16). Additionally, prolonged procedural durations have been associated with robot-assisted surgeries, although this may decrease with increased experience and refined systems (16).

The use of AI in ophthalmology

Ophthalmology stands out as one of the medical fields that has significantly benefited from and driven the adoption of advanced technologies, including AI and robotics (9,18,19). This is largely due to the transparency of eye structures and the feasibility of detailed imaging, lending itself well to data extraction and high-quality databases of digital images (20). AI presents a unique way to analyse this information and transform it into a useful tool for clinical decision-making (21).

The integration of AI into ophthalmology represents a profound paradigm shift, driven by the field’s inherent reliance on image-based diagnostics and the wealth of patient data available (21,22). This confluence of technological advancement and clinical demand positions AI as a transformative force, with applications spanning diagnosis, treatment, surgical intervention, patient education and healthcare delivery (19,23). Although still in its early stages, AI holds the potential to revolutionise ophthalmic practice to overcome human physiological limitations and enhance global eye health. This necessitates a nuanced discussion of current capabilities, limitations and the future trajectory of AI in ophthalmology (18-20).

Revolutionising diagnosis and screening

Artificial. intelligence algorithms, particularly those leveraging machine learning (ML) and deep learning (DL), have demonstrated remarkable success in diagnosing a wide array of ocular conditions with precision comparable to, or even exceeding, human experts (12,23). This is especially pertinent in conditions such as diabetic retinopathy (DR), age-related macular degeneration (AMD) and glaucoma, where AI systems can analyse retinal images, optical coherence tomography (OCT) scans and visual fields to detect early signs of disease and predict progression (22). For instance, AI algorithms have shown high sensitivity in detecting referable DR and severe DR, sometimes outperforming human experts (Table 2) (5,23).

Beyond common conditions, AI also shows promise in diagnosing paediatric eye diseases including strabismus, myopia, amblyopia, retinoblastoma and papilloedema, particularly aiding in the identification of subtle morphological differences in the optic disc or tumours from fundus images (4,19,24). The efficiency afforded by AI in these diagnostic tasks can significantly reduce screening time and diagnostic burden on ophthalmologists, improving patient outcomes through earlier detection and intervention (23).

AI integration in ophthalmology will offer comprehensive solutions for diagnosis, treatment planning and patient monitoring (1). AI technologies can be used to screen and diagnose a broad spectrum of eye conditions, including DR, glaucoma, AMD, retinopathy of prematurity (ROP) and cataracts—particularly in intraocular lens power calculations (2,10). AI is also valuable in managing anterior segment disorders such as those encountered in refractive surgery, keratoconus and dry eye disease (10). Imaging techniques integrated with AI have significantly automated screening processes, enabling early detection, timely intervention and enhanced prediction of disease progression, surgical outcomes and potential complications (1). Furthermore, AI supports treatment decision-making by leveraging OCT biomarkers—such as intraretinal fluid, subretinal fluid and central retinal thickness—to predict patient responses to anti-vascular endothelial growth factor (anti-VEGF) therapy. AI algorithms are also being used increasingly to assist in the planning and optimisation of laser photocoagulation procedures (10).

Current AI systems utilize deep neural networks to perform complex semantic segmentation of medical images, allowing them to identify and highlight anatomical and pathological zones. These systems can analyze the localization and severity of conditions like diabetic macular oedema (DME), allowing the AI to “reason” about the best placement for surgical interventions based on the individual’s anatomical structures (25). Platforms leverage Natural Language Processing (NLP) and Named Entity Recognition (NER) (specifically models like SoftLexicon-Glove-Word2vec) to extract key clinical information from electronic medical records (EMRs). Algorithms such as XGBoost then use this data to infer optimal diagnoses for diseases like retinal detachment and macular holes (26).

Transforming surgical procedures through AI and robotics

Ophthalmic surgery involves inherently delicate microsurgery, demanding exceptional precision and stability that can push the physiological limits of human surgeons (3,15). AI plays a crucial role in various stages of ophthalmic surgery, including candidate screening, surgical selection, postoperative prediction and real-time intraoperative guidance (18). For instance, machine learning models have been developed to automate the screening process for refractive surgery candidates, identify early-stage keratoconus, and even select expert-level laser surgery options (18).

Robotics, augmented by AI, is poised to address these challenges and expand the surgical repertoire. In the operating room, AI-driven tools enhance precision and safety by providing real-time feedback, assisting in accurate incisions and optimising surgical fluidics (23). Robotic systems, integrated with AI algorithms, can stabilise surgical instruments, filter tremors and perform precise manoeuvres, thereby minimising human error and reducing the likelihood of complications (2). Breakthroughs include robot-assisted subretinal drug delivery, retinal vein cannulation and advanced phacoemulsification for cataract surgery (27). While still largely in experimental stages, systems such as the IRISS (9) and the Preceyes robotic surgical system have demonstrated feasibility in human studies, including the successful performance of CCC and full cataract surgery (13).

Embodied artificial intelligence (EAI) integrates into physical entities like robots, allowing for real-time perception, learning, and dynamic interaction with the surrounding environment. This physical interaction enables EAI to perform complex tasks in ophthalmology, such as achieving micron-level surgical precision during procedures and providing bidirectional tactile feedback for visually impaired individuals (18).

The future envisions increasingly autonomous surgical steps, with surgeons providing strategic control and supervision. Robotics and AI are increasingly transforming ophthalmology by enhancing diagnostic accuracy, surgical precision and patient outcomes across a wide range of conditions. Robotic assistance has proven particularly valuable in vitreoretinal surgery, where it promotes overcoming human limitations such as tremor, allowing for delicate procedures, e.g., membrane peeling and subretinal injections (2). In corneal disease, AI aids diagnosis through imaging data analysis, and robotic systems have been explored for applications such as corneal transplantation (10). In strabismus, AI platforms assist in diagnostic and surgical planning tasks, while robotic systems have shown promise in simulated surgeries (28). Robotic technologies have also been applied in oculoplastic and orbital surgeries, including procedures like orbital fat decompression (29), underscoring the expanding role of these innovations in ophthalmic care.

Critical safety controls have been established for calculations and surgical decision support, including AI-based intra-ocular lens (IOL) power formulas such as Kane and Hill-RBF 3.0 that significantly improve refractive outcomes compared to traditional methods (18,24). Furthermore, robotic safety is bolstered by sophisticated mechanisms like Active Disturbance Rejection Controllers (ADRC) and speed look-ahead algorithms that precisely manage contact forces at the millinewton level, ensuring they remain within safe clinical limits to prevent permanent retinal damage (15,30). Additionally, automated systems that regulate fluidics help maintain a stable anterior chamber, protecting the corneal endothelium during surgical procedures (23).

Enhancing patient engagement and education

AI, particularly large language models (LLMs) such as ChatGPT, offers novel avenues for improving patient experience and education. These chatbots can provide dynamic, tailored responses to patient queries, from common symptoms to specific eye diseases such as cataracts and glaucoma (31). They can also summarise complex clinical information in patient-friendly language for pre- and postoperative conversations, potentially improving patient compliance and saving ophthalmologist time. Beyond direct patient interaction, generative AI can assist physicians and health systems in creating interactive patient education materials, such as discharge summaries and postoperative instructions, and facilitate multi-language translation, contributing to more equitable healthcare services (17,19,32).

Operational efficiencies and expanding access to care

The ability of AI to automate routine tasks and analyse high volumes of medical images can significantly reduce the burden on human clinicians, allowing them to focus on complex patient care and disease management (33,34). This is particularly impactful in tele-ophthalmology, which has emerged as a promising solution to improve access to eye care, especially for patients in remote or underserved areas. AI models integrated into tele-ophthalmology infrastructure can revolutionise eye care services by reducing costs, improving efficiency and increasing access to specialised care (23,34). Smartphone technology, merged with AI algorithms, offers unprecedented opportunities for diagnosis, monitoring and management of ocular conditions, facilitating timely, efficient and cost-effective screening (23,35). The concept of “ophthalmologist robot” devices further highlights the potential for automated non-dilated fundus and ocular surface imaging, making eye screening possible in remote areas without specialist ophthalmologists (36).

Addressing key limitations and practical challenges

Despite the promising advancements, several significant challenges obstruct the widespread adoption and full realisation of AI’s potential in ophthalmology. A primary concern is AI “hallucination”, where models generate false or non-logical information, which can be misleading and impact clinical decision-making. While some LLMs have shown commendable performance in ophthalmic knowledge assessments, their accuracy can vary significantly across subspecialties and is notably lower for image interpretation or calculation-based questions (31,32).

Data dependence is another critical limitation. AI algorithms heavily rely on extensive, high-quality, annotated datasets for training, which are not always readily available or sufficiently diverse to ensure accuracy across different demographic scenarios (19). The unique multi-ethnic makeup of populations may limit the generalisability of algorithms trained on different populations, necessitating validation studies or local model development (4,23,34).

A significant hurdle is the so-called “black box phenomenon”, where AI systems’ underlying mechanics are opaque, making it difficult for physicians to understand how and why a conclusion is reached (4,32). This lack of transparency can lead to distrust and automation bias, especially among less experienced physicians, who may passively adhere to incorrect AI recommendations (37).

The initial financial investment for AI infrastructure can be substantial, though it has the potential for long-term cost reductions (17).

The integration of AI and robotics into ophthalmology requires a substantial initial financial outlay, covering the acquisition of specialized equipment like fundus cameras, annual maintenance, service contracts, and extensive staff training (17,34). Despite these high startup costs, the investment has the potential for significant long-term cost reductions by automating data interpretation, streamlining clinical workflows, and improving diagnostic accuracy to reduce the frequency of patient visits (17,34). Data support these economic benefits; for instance, tele-glaucoma programs have saved 175.90 USD compared to conventional in-person examinations (34). Operational efficiencies also yield quantifiable savings, with one AI-driven verification tool saving 11 seconds per patient review, which translates to an estimated 127.11 hours of nursing time saved annually for a single department (38). On a societal scale, AI tools may help mitigate the massive economic burden of neurodegenerative diseases like Parkinson’s, which is projected to exceed $79 billion by 2037 (4).

The absence of AI training within ophthalmology curricula, covering foundational concepts in AI, machine learning, deep learning, and the underlying mathematical and statistical principles, represents a significant limitation. A grasp of these concepts enhances both diagnostic interpretation and clinical application (5). Therefore, integrating a structured AI curriculum for ophthalmology residents is essential.

Ethical, legal and societal implications

As AI and robotics become more integrated, ethical considerations are vital (34,39). These include ensuring data privacy and security through robust encryption and stringent access control, while questions pertaining to medical liability arising from machine error also need to be addressed (17). Algorithmic bias is a critical concern, as biased training data can lead to inequitable care across diverse patient populations (20).

There is consensus on the need for robust regulatory frameworks and comprehensive guidelines for the responsible deployment of AI. The American Academy of Ophthalmology (AAO) has begun incorporating AI content and ethical considerations into its Basic and Clinical Science Course (BCSC) textbooks and official policies, and has issued statements on copyright regarding AI training (18,32).

Societal factors such as the “digital divide” can create barriers to access (8). Furthermore, the potential for job displacement or automation raises concerns among some ophthalmologists, although most see AI as a supportive tool rather than a replacement (17,39).

Limitations of the study

As a narrative review, this study is limited by the absence of a systematic search strategy and formal quality appraisal, which could introduce selection bias and reduce reproducibility. The depth of analysis may vary across topics, and some relevant studies may have been overlooked. As a result, the findings reflect a broad synthesis of existing literature rather than a comprehensive or fully representative body of evidence; therefore, it should be interpreted with appropriate caution. But from the nature of a narrative review, the flexible approach allows for integration of diverse perspectives and identification of gaps, offering a structured framework for incorporating digital tools that can inform educators, policymakers, and researchers.

Conclusions

The prevailing sentiment is that AI should function as an assistive tool rather than a complete replacement for human expertise and clinical experience. Physicians are essential in critically evaluating AI outputs, particularly in ambiguous or borderline cases, and maintaining human oversight remains crucial. The future envisions a synergistic relationship where AI supports and augments human capabilities, enhancing efficiency, accuracy and patient safety.

The future of AI and robotics in ophthalmology is characterised by continuous innovation aimed at overcoming human physiological limitations, expanding the surgical repertoire, enhancing diagnostic accuracy and improving accessibility to care. The convergence of AI with advanced imaging modalities, robotics, smartphone technology and tele-ophthalmology promises to usher in an era of personalised, data-driven interventions and revolutionise global eye health.

To facilitate this synergy, medical education curricula must adapt. Future clinicians will need to be trained on the applications and limitations of AI, how to interpret AI results, and how to explain these results to patients. Organisations such as the AAO are updating their educational resources to include AI content and ethical considerations. Comprehensive curricula should cover fundamental AI principles, ethical guidelines, data privacy and practical skills in evaluating AI studies and employing automated deep learning platforms. This adaptation requires support from major organisations and multidisciplinary collaboration across departments such as bioinformatics, bioengineering, computer science and statistics.

However, realising this potential necessitates a concerted effort to address the practical, economic and ethical challenges that remain. By continuously refining AI algorithms, ensuring robust data governance, mitigating biases and investing in comprehensive medical education, the ophthalmic community can foster a safe, effective and patient-centred future where AI serves as a powerful collaborator, augmenting human expertise and ultimately leading to better patient outcomes worldwide.

Acknowledgments

We thank Ms. Annamarie du Preez, assistant director, Frik Scott Library, Faculty of Health Sciences, University of the Free State, for assistance with the literature search; and Dr. Daleen Struwig, medical writer/editor, Faculty of Health Sciences, University of the Free State, for technical and editorial preparation of the article.

Footnote

Provenance and Peer Review: This article was commissioned by the editorial office, Annals of Eye Science for the series “Optimizing Ophthalmology Surgery Training Through Active Learning Strategies”. The article has undergone external peer review.

Reporting Checklist: The authors have completed the Narrative Review reporting checklist. Available at https://aes.amegroups.com/article/view/10.21037/aes-25-48/rc

Peer Review File: Available at https://aes.amegroups.com/article/view/10.21037/aes-25-48/prf

Funding: None.

Conflicts of Interest: Both authors have completed the ICMJE uniform disclosure form (available at https://aes.amegroups.com/article/view/10.21037/aes-25-48/coif). The series “Optimizing Ophthalmology Surgery Training Through Active Learning Strategies” was commissioned by the editorial office without any funding or sponsorship. M.J.L. served as an unpaid Guest Editor of the series. The authors have no other conflicts of interest to declare.

Ethical Statement: The authors are accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.

Open Access Statement: This is an Open Access article distributed in accordance with the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International License (CC BY-NC-ND 4.0), which permits the non-commercial replication and distribution of the article with the strict proviso that no changes or edits are made and the original work is properly cited (including links to both the formal publication through the relevant DOI and the license). See: https://creativecommons.org/licenses/by-nc-nd/4.0/.

References

1. Kang D, Wu H, Yuan L, et al. A Beginner's Guide to Artificial Intelligence for Ophthalmologists. Ophthalmol Ther 2024;13:1841-55. [Crossref] [PubMed]
2. Mi H, MacLaren RE, Cehajic-Kapetanovic J. Robotising vitreoretinal surgeries. Eye (Lond) 2025;39:673-82. [Crossref] [PubMed]
3. Pandey SK, Sharma V. Robotics and ophthalmology: Are we there yet? Indian J Ophthalmol 2019;67:988-94. [Crossref] [PubMed]
4. Tukur HN, Uwishema O, Akbay H, et al. AI-assisted ophthalmic imaging for early detection of neurodegenerative diseases. Int J Emerg Med 2025;18:90. [Crossref] [PubMed]
5. Valikodath NG, Cole E, Ting DSW, et al. Impact of Artificial Intelligence on Medical Education in Ophthalmology. Transl Vis Sci Technol 2021;10:14. [Crossref] [PubMed]
6. Jin K, Ye J. Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives. Adv Ophthalmol Pract Res 2022;2:100078. [Crossref] [PubMed]
7. Rana MM, Akter J, Hanif MA. Next-gen vision: a systematic review on robotics transforming ophthalmic surgery. J Robot Surg 2025;19:452. [Crossref] [PubMed]
8. Wah JNK. Revolutionizing surgery: AI and robotics for precision, risk reduction, and innovation. J Robotic Surg 2025;19:47.
9. Alafaleq M. Robotics and cybersurgery in ophthalmology: a current perspective. J Robot Surg 2023;17:1159-70. [Crossref] [PubMed]
10. Hashemian H, Peto T, Ambrósio R Jr, et al. Application of Artificial Intelligence in Ophthalmology: An Updated Comprehensive Review. J Ophthalmic Vis Res 2024;19:354-67. [Crossref] [PubMed]
11. Swaminathan U, Daigavane S. Unveiling the Potential: A Comprehensive Review of Artificial Intelligence Applications in Ophthalmology and Future Prospects. Cureus 2024;16:e61826. [Crossref] [PubMed]
12. Ouzzani M, Hammady H, Fedorowicz Z, et al. Rayyan-a web and mobile app for systematic reviews. Syst Rev 2016;5:210. [Crossref] [PubMed]
13. Ahronovich EZ, Simaan N, Joos KM. A Review of Robotic and OCT-Aided Systems for Vitreoretinal Surgery. Adv Ther 2021;38:2114-29. [Crossref] [PubMed]
14. Taylor R, Jensen P, Whitcomb L, et al. A steady-hand robotic system for microsurgical augmentation. Int J Robot Res 1999;18:1201-10.
15. Wang N, Zhang X, Bano S, et al. Vision-based automatic control of a surgical robot for posterior segment ophthalmic surgery. IEEE Trans Autom Sci Eng 2025;22:6088-99.
16. Thirunavukarasu AJ, Hu ML, Foster WP, et al. Robot-Assisted Eye Surgery: A Systematic Review of Effectiveness, Safety, and Practicality in Clinical Settings. Transl Vis Sci Technol 2024;13:20. [Crossref] [PubMed]
17. Ahmed A, Fatani D, Vargas JM, et al. Physicians' Perspectives on ChatGPT in Ophthalmology: Insights on Artificial Intelligence (AI) Integration in Clinical Practice. Cureus 2025;17:e78069. [Crossref] [PubMed]
18. Nuliqiman M, Xu M, Sun Y, et al. Artificial Intelligence in Ophthalmic Surgery: Current Applications and Expectations. Clin Ophthalmol 2023;17:3499-511. [Crossref] [PubMed]
19. Madadi Y, Delsoz M, Khouri AS, et al. Applications of artificial intelligence-enabled robots and chatbots in ophthalmology: recent advances and future trends. Curr Opin Ophthalmol 2024;35:238-43. [Crossref] [PubMed]
20. Larkin F, He M. Embracing generative AI in ophthalmology. Br J Ophthalmol 2024;108:1333-4. [Crossref] [PubMed]
21. Kapoor R, Walters SP, Al-Aswad LA. The current state of artificial intelligence in ophthalmology. Surv Ophthalmol 2019;64:233-40. [Crossref] [PubMed]
22. Goktas P, Grzybowski A. Shaping the Future of Healthcare: Ethical Clinical Challenges and Pathways to Trustworthy AI. J Clin Med 2025;14:1605. [Crossref] [PubMed]
23. Olawade DB, Weerasinghe K, Mathugamage MDDE, et al. Enhancing Ophthalmic Diagnosis and Treatment with Artificial Intelligence. Medicina (Kaunas) 2025;61:433. [Crossref] [PubMed]
24. Maitra P, Puri A, Rishi P. Applications of artificial intelligence in pediatric ophthalmology: Part 2. Adv Ophthalmol Optom 2025;10:77-84.
25. Ilyasova NY, Demin NS. Application of artificial intelligence in ophthalmology for the diagnosis and treatment of eye diseases. Pattern Recognit Image Anal 2022;32:477-82.
26. Guo Y, Huang C, Sheng Y, et al. Improve the efficiency and accuracy of ophthalmologists' clinical decision-making based on AI technology. BMC Med Inform Decis Mak 2024;24:192. [Crossref] [PubMed]
27. Jin K, Li Y, Wu H, et al. Integration of smartphone technology and artificial intelligence for advanced ophthalmic care: A systematic review. Adv Ophthalmol Pract Res 2024;4:120-7. [Crossref] [PubMed]
28. Yamamoto S, Kuroki Y, Ide T, et al. Customization of a passive surgical support robot to specifications for ophthalmic surgery and preliminary evaluation. Jpn J Ophthalmol 2023;67:637-44. [Crossref] [PubMed]
29. Wang Y, Sun J, Liu X, et al. Robot-Assisted Orbital Fat Decompression Surgery: First in Human. Transl Vis Sci Technol 2022;11:8. [Crossref] [PubMed]
30. Tao Q, Liu J, Zheng Y, et al. Evaluation of an Active Disturbance Rejection Controller for Ophthalmic Robots with Piezo-Driven Injector. Micromachines (Basel) 2024;15:833. [Crossref] [PubMed]
31. Bahir D, Zur O, Attal L, et al. Gemini AI vs. ChatGPT: a comprehensive examination alongside ophthalmology residents in medical knowledge. Graefes Arch Clin Exp Ophthalmol 2025;263:527-36.
32. Heinke A, Radgoudarzi N, Huang BB, et al. A review of ophthalmology education in the era of generative artificial intelligence. Asia Pac J Ophthalmol (Phila) 2024;13:100089. [Crossref] [PubMed]
33. Gunasekeran DV, Zheng F, Lim GYS, et al. Acceptance and Perception of Artificial Intelligence Usability in Eye Care (APPRAISE) for Ophthalmologists: A Multinational Perspective. Front Med (Lausanne) 2022;9:875242. [Crossref] [PubMed]
34. Balas M, Micieli JA, Wong JCY. Integrating AI with tele-ophthalmology in Canada: a review. Can J Ophthalmol 2025;60:e337-43. [Crossref] [PubMed]
35. Romero-Aroca P, Fontoba-Poveda B, Garcia-Curto E, et al. Two Handheld Retinograph Devices Evaluated by Ophthalmologists and an Artificial Intelligence Algorithm. J Clin Med 2024;13:6935. [Crossref] [PubMed]
36. Li Q, Tan J, Xie H, et al. Evaluating the accuracy of the Ophthalmologist Robot for multiple blindness-causing eye diseases: a multicentre, prospective study protocol. BMJ Open 2024;14:e077859. [Crossref] [PubMed]
37. Kashiwagi K, Toyoura M, Mao X, et al. Influence of artificial intelligence on ophthalmologists' judgments in glaucoma. PLoS One 2025;20:e0321368. [Crossref] [PubMed]
38. Lin H, Huang X, Sheng Y, et al. Intelligent Verification Tool for Surgical Information of Ophthalmic Patients: A Study Based on Artificial Intelligence Technology. J Patient Saf 2025;21:62-8. [Crossref] [PubMed]
39. Chen S, Bai W. Artificial intelligence technology in ophthalmology public health: current applications and future directions. Front Cell Dev Biol 2025;13:1576465. [Crossref] [PubMed]