39 EyeWorld Asia-Pacific | March 2025 REFRACTIVE SURGERY deliberate incorporation of more representative datasets and continuous validation of AI systems across diverse patient populations. Clinician Skills May Decline Inversely To The Uptake Of AI The art of medicine is only refined through experience, and experience only grows with volume of case exposure over time. Furthermore, clinicians are uniquely positioned to take into account the combination of genetic, biological, environmental, psychological and socioeconomic factors that play a significant role in visual outcomes of refractive surgery, and particularly with respect to patient satisfaction. Managing the psychological aspect of refractive surgery is arguably just as important as the diagnosis and treatment itself, and the clinician’s expertise in human judgement and empathy as well as clinical expertise is vital. Biological systems are inherently complex and whereas AI certainly should be harnessed as a tool for large scale data processing, augmentation and refinement of diagnostic and treatment capabilities, the discerning judgement of the clinician remains of paramount importance. Furthermore, if an AI judgement makes a mistake and harm is caused, who is responsible? Is it the software company, the doctor, or the clinic? There must be clear rules about this to avoid confusion and to protect patient safety. Ultimately the surgeon’s role will be to interpret, justify and contextualise the options presented by AI and this can only be refined through experience - without which, patient safety may be severely jeopardized. AI And My Eye - The Designer’s Dream The mismatch of corneal and lens optical characteristics is probably the greatest source of dissatisfaction within refractive surgery, with refractive complications a distant second, given their relative rarity. The exciting potential of AI to “custom” design or allocate the perfect presbyopia correcting solution is very real and will require a collaborative effort between industries - the diagnosticians, the lens manufacturers, the laser manufacturers to name a few. We know that the laws of optics are fundamental and unchangeable; AI is not intended to replace them. However, AI can and should play a complementary role in managing external parameters that lie beyond the scope of the mathematical and physical models used to design and refine intraocular lenses or laser correction profiles. This, however, requires a level of transparency from manufacturers, who unfortunately are often reluctant to disclose their proprietary technologies. The question that must be asked then, is: is industry really ready to unite in this mission? About the Physicians Renato Ambrósio Jr., MD, PhD | Adjunct Professor of Ophthalmology, Federal University of the State of Rio de Janeiro, Rio de Janeiro, Brazil | dr.renatoambrosio@gmail.com Ella Faktorovich, MD | Pacific Vision Institute, San Francisco, California | ella@pacificvision.org Nambi Nallasamy, MD | Assistant Professor of Ophthalmology and Visual Sciences, Assistant Professor of Computational Medicine and Bioinformatics, University of Michigan, Kellogg Eye Center, Ann Arbor, Michigan | nnallasa@med.umich.edu Travis Redd, MD | Assistant Professor of Ophthalmology, School of Medicine, Oregon Health & Science University, Portland, Oregon | redd@ohsu.edu Relevant Disclosures Ambrósio: Alcon, Ambrósio Vision Academy, Brazilian Artificial Intelligence Networking in Medicine (BrAIN), Carl Zeiss Meditec, Mediphacos, Oculus Faktorovich: None Nallasamy: Recordati Rare Diseases Redd: None References 1. Maeda N, et al. Neural network classification of corneal topography. Preliminary demonstration. Invest Ophthalmol Vis Sci. 1995;36:1327–1335. 2. Ambrosio Jr R, Randleman JB. Screening for ectasia risk: what are we screening for and how should we screen for it? J Refract Surg. 2013;29:230–232. 3. Ambrósio Jr R, Belin M. Enhanced screening for ectasia risk prior to laser vision correction. Int J Keratoconus Ectatic Corneal Dis. 2017;6:23–33. 4. Ambrósio Jr R. Post-LASIK ectasia: twenty years of a conundrum. Semin Ophthalmol. 2019;34:66–68. 5. Dupps WJ, Seven I. A large-scale computational analysis of corneal structural response and ectasia risk in myopic laser refractive surgery. Trans Am Ophthalmol Soc. 2016;114:T1. 6. McGhee CNJ, et al. Contemporary treatment paradigms in keratoconus. Cornea. 2015;34 Suppl 10:S16–23. 7. Ambrósio Jr R, et al. Optimized artificial intelligence for enhanced ectasia detection using Scheimpflug-based corneal tomography and biomechanical data. Am J Ophthalmol. 2023;251:126–142. This article originally appeared in the December 2024 issue of EyeWorld. It has been slightly modified and appears here with permission from the ASCRS Ophthalmic Services Corp. Editors’ note: Dr. Tanya Trinh disclosed no relevant financial interests.
RkJQdWJsaXNoZXIy Njk2NTg0