Can AI Improve Accuracy of Refractive Surgery?

Author: Rasit Dinc

Introduction

Refractive surgery has revolutionized the field of ophthalmology, offering millions of people the opportunity to achieve clear vision without the need for glasses or contact lenses. Procedures like LASIK, PRK, and SMILE have become commonplace, with a high degree of success. However, the quest for even greater precision and better patient outcomes is perpetual. In recent years, artificial intelligence (AI) has emerged as a transformative force across various medical specialties, and ophthalmology is no exception. This article explores the burgeoning role of AI in enhancing the accuracy of refractive surgery, from preoperative planning to postoperative care, while also considering the current challenges and future potential.

AI-Powered Preoperative Planning: A Paradigm Shift

The success of any refractive procedure is heavily dependent on meticulous preoperative planning. This includes accurate patient selection, precise corneal measurements, and the development of a personalized treatment plan. AI, particularly machine learning (ML) algorithms, is proving to be an invaluable tool in this critical phase.

Deep learning models are adept at recognizing subtle patterns in complex datasets, such as corneal tomography and topography images [1]. These models can analyze a vast number of data points to identify patients who are ideal candidates for surgery and, more importantly, to flag those at higher risk of complications like postoperative ectasia [2]. For instance, AI-based systems can achieve high accuracy in determining a patient's suitability for corneal refractive surgery, in some cases exceeding 94% [3]. By leveraging large datasets, AI can help surgeons make more informed decisions, moving towards a more personalized and predictive approach to patient care.

Enhancing Surgical Precision with Artificial Intelligence

Beyond the planning stage, AI is also making its way into the operating room, contributing to greater surgical precision. One of the most significant applications is in the calculation of intraocular lens (IOL) power for cataract and refractive lens exchange surgeries. AI-based formulas have been shown to outperform traditional methods, especially in challenging cases such as highly myopic eyes, leading to more accurate refractive outcomes [4].

Furthermore, in procedures like ICL (Implantable Collamer Lens) implantation, AI algorithms can enhance surgical precision by predicting surgically induced astigmatism, refining the lens orientation, and optimizing the lens size for each individual eye [5]. This level of customization was previously unattainable and promises to reduce the incidence of residual refractive errors, a common reason for patient dissatisfaction.

The Role of AI in Postoperative Management

The benefits of AI extend into the postoperative period. AI tools can be utilized to monitor trends in a patient's vision recovery, including visual acuity, aberrometry, and contrast sensitivity. By analyzing this data over time, AI can help predict long-term visual outcomes and identify patients who may not be recovering as expected, allowing for timely intervention [6]. This proactive approach to postoperative care can lead to better final outcomes and a higher level of patient satisfaction.

Challenges and the Road Ahead

Despite the immense potential, the integration of AI into refractive surgery is not without its challenges. One study highlighted the potential for inaccuracies in AI-generated images used to illustrate corneal procedures, emphasizing that human-created illustrations are still superior in terms of anatomical realism [7]. This underscores the importance of rigorous validation and the need to view AI as a tool to augment, not replace, the expertise of the surgeon.

The future of AI in refractive surgery is bright. As algorithms become more sophisticated and datasets grow larger, we can expect to see even more advanced applications. AI will likely play a central role in the entire patient journey, from initial consultation to long-term follow-up, creating a seamless and highly personalized experience [8]. The continued collaboration between clinicians, researchers, and data scientists will be crucial in harnessing the full potential of AI to revolutionize refractive surgery and deliver on the promise of consistently perfect vision.

Conclusion

Artificial intelligence is poised to significantly improve the accuracy and outcomes of refractive surgery. From enhancing preoperative screening and personalizing treatment plans to increasing surgical precision and optimizing postoperative care, AI offers powerful new capabilities. While challenges remain, the ongoing advancements in AI technology promise a future where refractive surgery is safer, more predictable, and more effective than ever before, ultimately benefiting both patients and healthcare professionals.

References

[1] Hillman, L. (2024). AI expanding in refractive surgery. EyeWorld. Retrieved from https://www.eyeworld.org/2024/ai-expanding-in-refractive-surgery/

[2] Yoo, T. K., Ryu, I. H., Kim, J. K., Kim, J. K., & Lee, I. S. (2019). Adopting machine learning to automatically identify candidate patients for corneal refractive surgery. npj Digital Medicine, 2(1), 1-9. Retrieved from https://www.nature.com/articles/s41746-019-0135-8

[3] American Academy of Ophthalmology. (2020). AI May Help Identify Candidates for Refractive Surgery. EyeNet Magazine. Retrieved from https://www.aao.org/eyenet/article/ai-to-identify-candidates-for-refractive-surgery

[4] Ophthalmology Advisor. (2025). AI-Based IOL Calculation Outperforms Traditional Methods. Retrieved from https://www.ophthalmologyadvisor.com/news/ai-outperforms-traditional-iol-calculation-formulas-in-highly-myopic-eyes/

[5] Choi, J. Y., & Lee, H. K. (2025). AI & Refractive Surgeries: Laser Vision, Phakic IOLs. Annals of Eye Science, 10(1), 1-1. Retrieved from https://aes.amegroups.org/article/view/8271/html

[6] mivision. (n.d.). AI in Cataract and Refractive Surgery: The Implications and Outcomes. Retrieved from https://www.mieducation.com/pages/ai-in-cataract-and-refractive-surgery-the-implications-and-outcomes

[7] Petroff, D. J., & Petroff, C. J. (2024). Evaluating the Accuracy of Artificial Intelligence (AI) Generated Images of Corneal Refractive Surgery. Journal of Refractive Surgery, 40(5), 326-331. Retrieved from https://pubmed.ncbi.nlm.nih.gov/39318903/

[8] Akkara, J. D. (2025). AI for a clear eye: Revolutionizing refractive surgery. Kerala Journal of Ophthalmology, 37(1), 23-24. Retrieved from https://journals.lww.com/kjop/fulltext/2025/01000/ai_for_a_clear_eye__revolutionizing_refractive.23.aspx