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

You might also read

Related Articles

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

Sort by
Same author

Mechanisms for Anti-Inflammatory Activity of Gold Nanoparticles.

Combinatorial chemistry & high throughput screening·2026
Same author

Clinical Outcomes of Patients with SLE Treated with Belimumab, Without Versus With Prior Immunosuppressant Use: a US Claims Database Study.

Rheumatology and therapy·2025
Same author

Prediction of Lupus Classification Criteria via Generative AI Medical Record Profiling.

Biotech (Basel (Switzerland))·2025
Same author

Impact of a digital platform and flare risk blood biomarker index on lupus: A study protocol design for evaluating self efficacy and disease management.

Contemporary clinical trials communications·2025
Same author

Improved Health Outcomes in Patients with Systemic Lupus Erythematosus Following Early Belimumab Initiation Without Prior Immunosuppressant Use: A Real-World Descriptive Study.

Rheumatology and therapy·2024
Same author

Steroid-sparing effect of belimumab: results from a retrospective observational study of real-world data.

Lupus science & medicine·2023

Related Experiment Video

Updated: Jan 16, 2026

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model
07:40

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Published on: January 12, 2022

6.0K

Criteria and Protocol: Assessing Generative AI Efficacy in Perceiving EULAR 2019 Lupus Classification.

Gerald H Lushington1, Sandeep Nair1, Eldon R Jupe1

  • 1Progentec Diagnostics Inc., Oklahoma City, OK 73104, USA.

Diagnostics (Basel, Switzerland)
|September 27, 2025
PubMed
Summary
This summary is machine-generated.

Generative AI (genAI) shows high sensitivity for identifying systemic lupus erythematosus (SLE) negativity but struggles with positivity. The AI confidently identifies SLE-positive cases but may misclassify some as undifferentiated connective tissue disorder (UCTD).

Keywords:
American College of Rheumatology (ACR)European Alliance of Associations for Rheumatology (EULAR)antinuclear antibody (ANA)disease classificationgenerative artificial intelligence (genAI)natural language processing (NLP)systemic lupus erythematosus (SLE)undifferentiated connective tissue disorder (UCTD)

More Related Videos

Analyses of Proteinuria, Renal Infiltration of Leukocytes, and Renal Deposition of Proteins in Lupus-prone MRL/lpr Mice
09:43

Analyses of Proteinuria, Renal Infiltration of Leukocytes, and Renal Deposition of Proteins in Lupus-prone MRL/lpr Mice

Published on: June 8, 2022

3.4K
The bm12 Inducible Model of Systemic Lupus Erythematosus SLE in C57BL/6 Mice
12:04

The bm12 Inducible Model of Systemic Lupus Erythematosus SLE in C57BL/6 Mice

Published on: November 1, 2015

18.6K

Related Experiment Videos

Last Updated: Jan 16, 2026

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model
07:40

Experimental Autoimmune Uveitis: An Intraocular Inflammatory Mouse Model

Published on: January 12, 2022

6.0K
Analyses of Proteinuria, Renal Infiltration of Leukocytes, and Renal Deposition of Proteins in Lupus-prone MRL/lpr Mice
09:43

Analyses of Proteinuria, Renal Infiltration of Leukocytes, and Renal Deposition of Proteins in Lupus-prone MRL/lpr Mice

Published on: June 8, 2022

3.4K
The bm12 Inducible Model of Systemic Lupus Erythematosus SLE in C57BL/6 Mice
12:04

The bm12 Inducible Model of Systemic Lupus Erythematosus SLE in C57BL/6 Mice

Published on: November 1, 2015

18.6K

Area of Science:

  • Clinical Informatics
  • Artificial Intelligence in Healthcare
  • Rheumatology

Background:

  • Electronic health records (EHRs) and legacy medical records (MRs) present challenges in efficient data processing.
  • Information overload from excessive documentation hinders clinical workflows.
  • Generative AI (genAI) offers potential for automated MR summarization and characterization.

Purpose of the Study:

  • To evaluate the efficacy of a two-pass genAI strategy for classifying systemic lupus erythematosus (SLE).
  • To assess genAI's performance in differentiating SLE, undifferentiated connective tissue disorder (UCTD), and non-SLE cases using the EULAR 2019 criteria.
  • To analyze the performance metrics of genAI in evaluating specific SLE diagnostic criteria.

Main Methods:

  • Digitization of 78 individuals' medical records (MRs).
  • Implementation of a two-pass generative AI (genAI) assessment using Claude 3.5 LLM.
  • Application of the 22-criteria EULAR 2019 model for SLE classification.

Main Results:

  • Antinuclear antibody (ANA) criterion showed high sensitivity (0.78) and PPV (0.85) for SLE negativity but marginal specificity (0.60).
  • Averaged across 21 criteria, genAI demonstrated high specificity (0.54) for SLE positivity but a tendency to misclassify positives as UCTD.
  • GenAI exhibited confident SLE negativity assessment (high sensitivity) but weaker positivity assessment.

Conclusions:

  • GenAI provides confident assessments for SLE negativity but is less reliable for positivity.
  • The AI's specificity supports confident SLE-positive assertions but may lead to misclassification of clinical positives as UCTD.
  • Further refinement of genAI models is needed for accurate SLE classification, especially differentiating between SLE and UCTD.