Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: May 11, 2026

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies

Published on: November 1, 2024

Rethinking scale in ophthalmic artificial intelligence: from bigger models to smarter clinical reasoning.

Kai Jin^1,2, Kaikai Zhao^3,4,5, Rupesh Agrawal^6,7,8,9,10

¹Eye Center of Second Affiliated Hospital, School of Medicine, Zhejiang University, Hangzhou, China. jinkai@zju.edu.cn.

NPJ Digital Medicine

|May 9, 2026

Summary

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Low-concentration povidone-iodine for the prevention of intraocular infections in ophthalmic surgery.

Current opinion in ophthalmology·2021

Same author

Glaucomatous or Non-glaucomatous Optic Neuropathy-It Is a Question?

American journal of ophthalmology·2021

Same author

Analysis of visual disability in Buenos Aires, Argentina. Pathologic myopia is the leading cause in working age.

Medicina·2021

Same author

Pioneers in neurology: Charles Miller Fisher (1913-2012).

Journal of neurology·2021

Same author

The 100 most-cited papers on age-related macular degeneration: a bibliographic perspective.

BMJ open ophthalmology·2021

Same author

Combination of Inverted ILM Flap Technique and Subretinal Fluid Application Technique for Treatment of Chronic, Persistent and Large Macular Holes.

Ophthalmology and therapy·2021

Advances in ophthalmic artificial intelligence (AI) show promise, but clinical trust is low. Future AI development must focus on trustworthy, skill-efficient systems integrating diverse data and uncertainty awareness for safe clinical use.

Area of Science:

Ophthalmology
Artificial Intelligence
Medical Informatics

Background:

Recent progress in ophthalmic artificial intelligence (AI) has led to improved performance on benchmark datasets.
Despite performance gains, widespread clinical adoption and trust in AI systems remain significant challenges.

Purpose of the Study:

To advocate for a shift in AI development from mere data and model scaling.
To emphasize the need for trustworthy, skill-efficient AI systems in ophthalmology.
To highlight the importance of integrating multimodal evidence, external knowledge, and uncertainty-aware reasoning.

Main Methods:

Conceptual framework development advocating for advanced AI integration.
Discussion of ophthalmology as a testbed for agentic AI.

Related Experiment Videos

Last Updated: May 11, 2026

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies

An Automated Squint Method for Time-syncing Behavior and Brain Dynamics in Mouse Pain Studies

Published on: November 1, 2024

Emphasis on rigorous validation, workflow integration, and evaluation frameworks.

Main Results:

Current AI progress is insufficient for clinical trust.
A new direction focusing on trustworthy, skill-efficient AI is proposed.
Ophthalmology is identified as a suitable domain for testing agentic AI.

Conclusions:

Safe clinical translation of AI requires moving beyond performance metrics.
Integration of multimodal data, external knowledge, and uncertainty quantification is crucial.
Robust validation and evaluation aligned with clinical decision-making are essential for real-world AI deployment in ophthalmology.