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 28, 2026

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium
06:16

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium

Published on: July 28, 2023

Comparative Analysis of General-Purpose vs. Domain-Specific Multimodal Models for Diabetic Retinopathy

Mohammad Iqbal Nouyed1, Mohammad Al-Mamun2, Donald A Adjeroh3

  • 1Department of Microbiology, Immunology and Cell Biology, West Virginia University, Morgantown, WV 26506, USA.

Diagnostics (Basel, Switzerland)
|May 27, 2026
PubMed
Summary

Related Concept Videos

Diabetic Retinopathy01:27

Diabetic Retinopathy

DefinitionDiabetic retinopathy is a microvascular complication of diabetes affecting the retinal blood vessels.Risk FactorsDiabetic retinopathy is present in almost all individuals with type 1 diabetes and more than 60% of those with type 2 diabetes after two decades of disease.The risk increases with poor glycemic control, hypertension, dyslipidemia, smoking, pregnancy, and puberty.Although cataracts and glaucoma are also more frequent in people with diabetes, retinopathy remains the leading...

You might also read

Related Articles

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

Sort by
Same author

Text-dominant decision-making by large multimodal models in dermatology clinical challenges. Comment on "AI-assisted dermatologic diagnosis using a large language model".

Journal of the American Academy of Dermatology·2026
Same author

Variable performance of 5 detection methods for identifying intravenous fluid contamination in basic metabolic panels at an academic medical center.

Laboratory medicine·2026
Same author

Recent advances in defending the privacy attacks of large language models for healthcare applications: a concise review.

Frontiers in artificial intelligence·2026
Same author

Synthetic data-augmented machine learning for 30-day readmission prediction in patients with chronic conditions: a retrospective real-world study.

BMJ open·2026
Same author

Prompt-based bioinformatic pipeline generation for a multi-step metaviral workflow.

Bioinformatics advances·2026
Same author

Uncovering the genetic architecture of pungency, carotenoids, and flavor in <i>Capsicum chinense</i> via TWAS-mGWAS integration and spatial transcriptomics.

Horticulture research·2025
Same journal

Correction: Luca et al. Global and Regional Diagnostic Results of Progress Toward Cervical Cancer Elimination, According to the WHO Strategy: A Systematic Literature Review with Narrative Synthesis. <i>Diagnostics</i> 2026, <i>16</i>, 1224.

Diagnostics (Basel, Switzerland)·2026
Same journal

Association Between Systemic Inflammatory Response Biomarkers and Disease Activity in Systemic Lupus Erythematosus: A Multi-Center Retrospective Study.

Diagnostics (Basel, Switzerland)·2026
Same journal

Vertebrogenic Low Back Pain and Basivertebral Nerve Ablation: A Review of Mechanisms, Imaging-Driven Selection, and Clinical Outcomes.

Diagnostics (Basel, Switzerland)·2026
Same journal

Multivalvular Carcinoid Heart Disease: The Role of Echocardiography in Diagnosis and Selection for Heterotopic Bicaval Valve Implantation.

Diagnostics (Basel, Switzerland)·2026
Same journal

Data-Efficient and Explainable Multimodal Survival Prediction in NSCLC Using Deep Image Embeddings, Clinical Variables, and Gradient-Boosted Trees.

Diagnostics (Basel, Switzerland)·2026
Same journal

Anomalous Left Coronary Artery from the Pulmonary Artery: Cinematic Volume Rendering Technique for Enhanced Anatomic Visualization.

Diagnostics (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

General-purpose AI models like Gemini 3 and GPT-5.2 show promise in diagnosing diabetic retinopathy, achieving accuracy comparable to specialized models. However, domain-specific models like MedSigLIP offer superior performance for retinal image analysis.

Area of Science:

  • Artificial Intelligence in Medical Imaging
  • Ophthalmology AI
  • Diabetic Retinopathy Detection

Background:

  • Multimodal foundation models, both general-purpose and domain-specific, are emerging as powerful tools for medical image analysis.
  • Evaluating the diagnostic capabilities of various AI models for diabetic retinopathy classification is crucial for clinical adoption.

Purpose of the Study:

  • To assess the classification accuracy of diabetic retinopathy versus normal fundus images using diverse AI models.
  • To compare the performance of general-purpose conversational models against specialized ophthalmology models.

Main Methods:

  • Zero-shot, few-shot prompting, linear probing, and fine-tuning techniques were applied to evaluate model performance.
  • Models tested included general-purpose (Gemini 3 Flash, GPT-5.2, Pixtral-Large), medical-specific (MedGemma-1.5, MedSigLIP), and ophthalmology-specific (RETFound, EyeCLIP).
Keywords:
diabetic retinopathyfundus imagesimage classificationlarge multimodal models

Related Experiment Videos

Last Updated: May 28, 2026

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium
06:16

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium

Published on: July 28, 2023

Main Results:

  • MedSigLIP achieved the highest accuracy (94.8%), followed by MedGemma-1.5 (88.2%) and Gemini 3 (88.5%).
  • General-purpose models like GPT-5.2 and Gemini 3 demonstrated competitive zero-shot accuracy, comparable to fine-tuned specialized models.
  • Domain-specific models generally offered higher accuracy and stability, while general-purpose models provided flexibility and interactive reasoning.

Conclusions:

  • A trade-off exists between the specialization of domain-specific models and the flexibility of general-purpose multimodal models.
  • General-purpose models offer accessibility and adaptability, serving as valuable complementary tools for retinal disease screening and clinical decision support.
  • Specialized models like MedSigLIP currently provide superior accuracy for diabetic retinopathy classification.