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 Concept Videos

Glaucoma: Overview01:25

Glaucoma: Overview

1.6K
Glaucoma is an eye condition characterized by increased intraocular pressure that damages the retina and optic nerve, leading to irreversible blindness if left untreated. The human eye has various components, including the cornea, iris, pupil, lens, and optic nerve. Aqueous humor is secreted by the epithelium of the ciliary body in the posterior chamber and flows through the trabecular meshwork and canal of Schlemm, maintaining normal intraocular pressure. The trabecular meshwork and the canal...
1.6K
Open Angle Glaucoma: Treatment01:27

Open Angle Glaucoma: Treatment

1.1K
In open-angle glaucoma, the iridocorneal angle remains open, but the trabecular meshwork becomes stiff, slowing down the outflow of aqueous humor. This causes a buildup of aqueous humor in the anterior chamber, leading to a sudden increase in intraocular pressure. The treatment for open-angle glaucoma focuses on reducing the elevated intraocular pressure by either decreasing the secretion of aqueous humor or increasing its outflow.
Drugs such as carbonic anhydrase inhibitors, α2- and...
1.1K

You might also read

Related Articles

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

Sort by
Same author

Leveraging Advanced AI Frameworks for Dual PPAR α/γ Agonist Discovery in Alzheimer's Disease.

ACS chemical neuroscience·2026
Same author

Comparing Computational Pathology Foundation Models using Representational Similarity Analysis.

Proceedings of machine learning research·2026
Same author

Benchmarking GPT-5, LLaMA, and Mistral for Clinical Named Entity Recognition in Ophthalmology Progress Notes.

Translational vision science & technology·2026
Same author

Improving Fairness and Mitigating Bias in Multicenter Electronic Health Records Models to Predict Glaucoma Outcomes.

Ophthalmology science·2026
Same author

Decline of Visual Function and Risk of Legal Blindness With Age in RPGR -Associated Retinal Degeneration: A Multicenter Study.

Clinical & experimental ophthalmology·2026
Same author

Addressing Generalizability in Clinical Named Entity Recognition: Federated Learning or Large Language Models?: A Case Study on Visual Acuity Extraction from US and UK Eye Institutes.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026

Related Experiment Video

Updated: Mar 7, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K

Evaluating the Performance of Large Language Models for Named Entity Recognition in Ophthalmology Clinical Free-Text

Iyad Majid1, Vaibhav Mishra1, Rohith Ravindranath1

  • 1Stanford University School of Medicine, Palo Alto, CA, United States.

AMIA ... Annual Symposium Proceedings. AMIA Symposium
|May 26, 2025
PubMed
Summary

Modern large language models (LLMs) like GPT-4 significantly outperform Bidirectional Encoder Representations from Transformers (BERT) models in extracting ophthalmic medication details from clinical notes, enhancing patient care.

More Related Videos

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.6K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.6K

Related Experiment Videos

Last Updated: Mar 7, 2026

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

1.3K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

16.6K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.6K

Area of Science:

  • Natural Language Processing
  • Medical Informatics
  • Artificial Intelligence in Healthcare

Background:

  • Accurate extraction of medication information from clinical notes is crucial for patient safety and care.
  • Traditional Natural Language Processing (NLP) models, such as Bidirectional Encoder Representations from Transformers (BERT), have been used for named entity recognition (NER) in clinical text.
  • Evaluating the performance of newer Large Language Models (LLMs) against established models in specialized domains is essential.

Purpose of the Study:

  • To compare the performance of various LLMs (ChatGPT-3.5, ChatGPT-4, PaLM 2, Gemini) against fine-tuned BERT-based models (BERT, BioBERT, ClinicalBERT, DistilBERT, RoBERTa) for identifying medication entities in ophthalmology progress notes.
  • To assess the efficacy of these models in a highly domain-specific medical text analysis task.
  • To determine the potential of LLMs in improving medical NER and patient care.

Main Methods:

  • A dataset of 5,520 lines of annotated ophthalmology progress notes from 480 patients was used.
  • The data was divided into training, validation, and testing sets.
  • LLMs were evaluated directly, while BERT-based models were fine-tuned on the training set for medication entity recognition (names, routes, frequencies).

Main Results:

  • GPT-4 achieved the highest performance with a macro-averaged F1 score of 0.962 on the test set.
  • Among the fine-tuned BERT models, BioBERT demonstrated the best performance with a macro-averaged F1 score of 0.875.
  • Modern LLMs significantly outperformed BERT models in this specialized ophthalmic medication identification task.

Conclusions:

  • Large Language Models, particularly GPT-4, show superior performance compared to BERT-based models for extracting medication information from specialized clinical text.
  • LLMs hold significant promise for advancing medical named entity recognition and improving the quality of patient care.
  • The findings highlight the potential of LLMs to enhance clinical data analysis and support healthcare professionals.