Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 26, 2026

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter
05:14

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter

Published on: September 16, 2025

Artificial intelligence in refractive surgery: progress, challenges, and future directions.

Yuke Ji1, Lu Xie2, Fangyan Liu2

  • 1Shenzhen Eye Hospital, Jinan University, Shenzhen, Guangdong, China.

Frontiers in Cell and Developmental Biology
|May 25, 2026
PubMed
Summary

Related Concept Videos

Angle Closure Glaucoma: Treatment01:28

Angle Closure Glaucoma: Treatment

Angle-closure glaucoma, or closed-angle glaucoma, is an eye condition where the iris bulges out and blocks the iridocorneal angle, resulting in a buildup of aqueous humor and increased intraocular pressure. Immediate medical attention is necessary due to the sudden onset of symptoms. The treatment for angle-closure glaucoma includes short-term and long-term approaches. Short-term treatment involves using eye drops like pilocarpine to lower intraocular pressure by increasing aqueous humor...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Preoperative Nonpharmacological Anxiety Management in Adult Ophthalmic Surgery: A Scoping Review.

Journal of perianesthesia nursing : official journal of the American Society of PeriAnesthesia Nurses·2026
Same author

Bacteria-derived glutarate mitigates Alzheimer's disease model pathology through autophagy-lysosomal pathway.

Cell communication and signaling : CCS·2026
Same author

Bacteria-derived equol alleviates Aβ toxicity in C. elegans through PEK-1-associated UPRer activation.

Biochemical and biophysical research communications·2026
Same author

Plasma albumin and other indicators as risk factors for delayed neurocognitive recovery in elderly patients undergoing orthopedic surgery.

BMC surgery·2026
Same author

Active fluidics at lower intraocular pressure reduces intraoperative discomfort during phacoemulsification: a propensity score-matched cohort study.

Frontiers in medicine·2026
Same author

Direct Regeneration of Spent LiNi<sub>0.8</sub>Co<sub>0.1</sub>Mn<sub>0.1</sub>O<sub>2</sub> into Ce-Doped Single-Crystal Cathodes.

Chem & bio engineering·2026
Same journal

Epigenetic plasticity and chemoresistance in cancer: mechanisms, biomarkers, and translational opportunities for real-world evidence.

Frontiers in cell and developmental biology·2026
Same journal

Matched embryo-endometrium RNA-seq reveals coordinated but asymmetric transcriptomic reprogramming at the onset of early equine pregnancy.

Frontiers in cell and developmental biology·2026
Same journal

Myelin development in the peripheral nervous system of <i>Trachemys scripta</i>.

Frontiers in cell and developmental biology·2026
Same journal

A deep learning-based classification method for subclinical zonular laxity in AS-OCT images.

Frontiers in cell and developmental biology·2026
Same journal

Advancing fat graft survival: from adipose-derived stem cell mechanisms to next-generation regenerative strategies.

Frontiers in cell and developmental biology·2026
Same journal

CRISPR-based next-generation molecular diagnostics for bone infection.

Frontiers in cell and developmental biology·2026
See all related articles
This summary is machine-generated.

This review explores how artificial intelligence is changing eye surgery. It looks at how computer models help doctors pick the right patients, plan surgeries, and predict healing issues. While these tools show great promise for making procedures more precise, the authors highlight hurdles like data consistency and ethical concerns that must be addressed.

Area of Science:

  • Ophthalmology research within artificial intelligence
  • Clinical refractive surgery outcomes research

Background:

Ophthalmology currently lacks a unified framework for integrating advanced computational tools into routine clinical practice. Prior research has shown that traditional surgical planning often relies on population-based averages rather than patient-specific metrics. This gap motivated a closer look at how automated systems might improve surgical accuracy. It was already known that machine learning models could process complex ocular imaging data efficiently. That uncertainty drove the need to synthesize recent evidence regarding model performance in vision correction. No prior work had resolved how these technologies translate across different surgical platforms. Investigators have long sought ways to minimize postoperative complications through predictive analytics. This review addresses the current landscape of digital integration within the field of refractive medicine.

Purpose Of The Study:

The aim of this review is to summarize recent progress in applying advanced computational models to refractive surgery and lens procedures. Researchers sought to evaluate how these technologies address the growing need for personalized surgical planning. The study investigates the utility of these tools in preoperative screening and the prediction of postoperative healing issues. This work addresses the specific problem of transitioning from standardized protocols to individualized patient management. The authors were motivated by the rapid evolution of digital tools in the medical field. They aimed to identify both the potential benefits and the remaining hurdles for clinical adoption. This review provides a clear picture of how automated systems are currently utilized in vision correction. The investigation clarifies the current state of digital integration to inform future clinical practices.

Keywords:
artificial intelligencecorneal refractive surgerydeep learningimplantable collamer lensmachine learningrefractive surgerymachine learningdeep learningophthalmologyclinical decision support

Frequently Asked Questions

The researchers propose that these systems improve outcomes by enabling personalized surgical planning and preoperative screening. Unlike traditional methods that use population averages, these models leverage patient-specific data to tailor interventions, thereby reducing the risk of postoperative complications compared to standardized protocols.

The authors identify machine learning and deep learning as the primary computational architectures. These tools differ from conventional statistical software by their ability to process high-dimensional ocular imaging data, which allows for more nuanced predictions than standard linear regression models used in previous decades.

The authors argue that algorithm interpretability is necessary to ensure clinicians understand how a model reaches its recommendation. Without this transparency, surgeons may struggle to trust automated outputs, creating a barrier to adoption that does not exist with traditional, rule-based clinical guidelines.

Related Experiment Videos

Last Updated: May 26, 2026

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter
05:14

Comparison of Agreement and Accuracy using Binocular Wavefront Optometer with Autorefractor and Phoropter

Published on: September 16, 2025

Main Methods:

The review approach involved a systematic synthesis of recent literature regarding computational applications in ocular procedures. Investigators examined studies focusing on machine learning and deep learning architectures specifically applied to corneal and lens-based interventions. The team evaluated evidence concerning preoperative screening protocols and surgical planning methodologies. They assessed how various models predict outcomes after vision correction. The authors scrutinized existing barriers to implementation, including technical limitations and ethical requirements. This analysis focused on identifying trends in how digital tools process clinical information. The researchers compared findings across multiple studies to determine the current state of model integration. This methodology provided a comprehensive overview of the field without conducting new primary experiments.

Main Results:

Key findings from the literature indicate that predictive models significantly enhance the accuracy of preoperative candidate selection. The review shows that deep learning architectures excel at identifying complex patterns in corneal imaging that human observers might overlook. Evidence suggests that these tools effectively reduce the incidence of unexpected postoperative complications by providing personalized risk assessments. The authors report that current systems are successfully transitioning from static protocols to dynamic, data-driven management strategies. Findings demonstrate that while model performance is high, the lack of standardized data formats limits broader application across different clinical centers. The literature indicates that cross-device compatibility remains a significant challenge for existing algorithms. Results highlight that interpretability issues often hinder the adoption of these models in high-stakes surgical environments. The synthesis confirms that digital decision-support systems are currently improving the precision of vision correction procedures.

Conclusions:

The authors suggest that algorithmic support systems are shifting surgical management toward highly individualized care models. These tools provide a pathway for enhancing precision beyond what standard protocols currently offer. Researchers emphasize that overcoming data standardization hurdles remains a prerequisite for widespread clinical adoption. Interpretability of complex models must improve to ensure surgeons trust automated recommendations during critical decision-making phases. The review notes that cross-device compatibility is essential for the seamless integration of these technologies into diverse hospital settings. Ethical considerations regarding patient data privacy and automated accountability require careful ongoing evaluation by the medical community. Future progress depends on creating robust, transparent frameworks that support clinicians rather than replacing their judgment. This synthesis confirms that digital innovation is fundamentally altering the trajectory of modern vision correction procedures.

The authors describe data as the foundation for training predictive models. High-quality, standardized datasets are required to ensure that algorithms perform reliably across different patient populations, contrasting with fragmented data sources that often lead to poor model generalization.

The researchers measure success through the ability of models to predict postoperative complications and optimize surgical outcomes. This phenomenon is evaluated by comparing the accuracy of AI-assisted predictions against historical clinical data and conventional prognostic benchmarks used by surgeons.

The authors imply that these systems will enable a transition toward automated and precise surgical correction. They suggest that while these tools currently support decision-making, they possess the potential to redefine the standard of care by moving away from rigid, one-size-fits-all surgical approaches.