Feb 10, 2025

Add topic to email alerts Receive an email when new articles are posted on Please provide your email address to receive an email when new articles are posted on . Subscribe Added to email alerts Back to Healio We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com . Back to Healio AI has quietly revolutionized the field of ophthalmology. While the concept of AI may evoke futuristic images of robots and automation, the reality is that many of us have been integrating AI into our practices for years without even realizing it. This article aims to demystify AI in cataract surgery and showcase how it enhances precision, improves patient outcomes and streamlines workflow. Figure 1. Iris registration accounts for cyclotorsion with a high degree of accuracy. Source: Joshua K. Duncan, DO Ophthalmology’s journey into AI Early AI applications in ophthalmology focused on retinal imaging and diagnostics, specifically for the detection and diagnosis of diabetic retinopathy. These early AI systems used deep learning algorithms to analyze retinal photographs for warning signs such as microaneurysms, hemorrhages and exudates with a high degree of accuracy. The application of AI in retinal imaging was groundbreaking, demonstrating the potential of AI to perform as well as, or even better than, human experts in certain diagnostic tasks. It also paved the way for its broader application across other areas of ophthalmology, including cataract surgery. The evolution of AI in cataract surgery Advancements in AI for cataract surgery have been incremental. Initial advancements, including the emergence of AI-driven IOL power calculators such as the Hill-RBF and various surgical management systems, quietly began to change how we approach cataract surgery. IOL calculation formulas. One of the earliest and most impactful uses of AI for cataract surgery is IOL calculation formulas such as the Hill-RBF calculator. Unlike traditional mathematical IOL calculation formulas, the Hill-RBF uses pattern recognition and a sophisticated form of data interpolation to provide more accurate calculations based on a vast dataset of surgical outcomes. The advanced self-validating method for IOL power selection has significantly improved our ability to predict refractive outcomes, particularly in eyes with complex biometry. Surgery planners. Surgery planners provide instant access to collated and relevant patient information from a variety of sources. In our practice, we use the Veracity surgery planner (Carl Zeiss Meditec). This system creates a seamless digital workflow by integrating data from electronic health record systems and diagnostic devices. This and other surgery planning software help optimize surgical plans, streamline workflow and facilitate better decision-making for patients. It integrates directly with biometry and topography devices, which reduces the risk for human error, enhancing safety and streamlining our workflow by automating many time-consuming tasks. EHR systems. Our EHR system, Modernizing Medicine, also leverages AI to improve efficiency and accuracy. It uses predictive modeling based on past patient encounters to suggest treatment plans and streamline documentation. Recently, new features such as voice recognition and real-time transcription further enhance our ability to provide personalized and precise patient care. Figure 2. Wireless connectivity between Ally and clinic-based topographers and biometers, using AI, helps with astigmatic surgical planning and operative precision. Laser cataract systems. The Ally laser system (Lensar) is a prime example of cutting-edge AI in cataract surgery. Two recent studies showed that improved accuracy of 3D reconstructions of the cornea and lens reduced phacoemulsification time as well as overall intraoperative case time with the Lensar laser (Morley and colleagues). Additionally, Ally uses AI to predictively locate iris anatomical markers for confident iris registration. This accounts for cyclotorsion and ensures precise corneal incision placement and astigmatic correction, eliminating the need for manual marking, which is a common source of human error. As a result, safety and accuracy are improved. The Ally platform also uses AI densitometry to adjust the fragmentation pattern based on the lens morphology and cataract density in real time. This can be accomplished by analyzing the surgeon’s baseline settings and using AI to adjust parameters such as spot spacing to achieve better cleavage. Such adaptability not only optimizes fragmentation patterns to increase surgical efficiency and reduce phaco energy, but we also see less corneal edema postoperatively, improved day 1 surgical outcomes and enhanced patient satisfaction. At this time, no other laser unit for cataract surgery incorporates AI. Most, however, integrate data from topographers and other diagnostic tools, ensuring that each procedure is tailored to the patient’s unique surgical plan. Such advances minimize the need for manual adjustments and enhance the accuracy of incisions and lens fragmentation. The impact of AI on workflow and patient experience AI has a profound impact on both our workflow and patient experience. Automated data entry, integrated diagnostic information and optimized fragmentation patterns — among other developments — help me focus more on patient care. This efficiency not only reduces the risk for errors and surgical complications but also allows us to see more patients without compromising the quality of care. From the patient’s perspective, AI-driven technologies contribute to better surgical outcomes and a more streamlined experience. For instance, the ability of the Ally system to adjust in real time, based on cataract density, ensures a more precise and efficient procedure. Patients benefit from shorter recovery time and fewer complications, enhancing their overall satisfaction. As we continue to explore and integrate AI into cataract surgery, we not only expand our capabilities but also pave the way for a safer and more efficient future in ophthalmology. References: Hill-RBF calculator version 3.0. https://rbfcalculator.com/online/index.html . Accessed Jan. 10, 2025. Morley D, et al. Multi-device pupil, limbus, and eyelid segmentation using deep learning. Presented at: Association for Research in Vision and Ophthalmology meeting; May 5-9, 2024; Seattle. Morley D, et al. Scheimpflug image segmentation using deep learning. Presented at: Association for Research in Vision and Ophthalmology meeting; May 5-9, 2024; Seattle. For more information: Joshua K. Duncan, DO, a cataract, cornea and refractive surgeon with Horizon Eye Specialists & LASIK Center in Arizona, can be reached at josh.kyle.duncan@gmail.com . Published by: