Performance of Large Language Models in Differentiating Systemic Lupus Erythematosus From Mimicking Conditions Using the 2019 EULAR / ACR Criteria: A Comparative Analysis
International Journal of Rheumatic Diseases · 2026-05 · 29 (5)
DOI: 10.1111/1756-185x.70713 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift International Journal of Rheumatic Diseases, online erschienen am 25.05.2026. Verfasst von Mirza Zaka Pratama und 3 weiteren Autor:innen. Beteiligte Einrichtung: Rheumatology Division, Internal Medicine Department, Dr Saiful General Hospital, Brawijaya University, Malang, Indonesia. Hauptthemen laut MEDLINE: Lupus Erythematosus, Systemic, Large Language Models, Rheumatology, Decision Support Techniques. Die Arbeit nennt 23 Literaturangaben.
Abstract (Originalsprache)
Introduction
Systemic Lupus Erythematosus (SLE) presents a significant diagnostic challenge for clinicians due to its diverse clinical manifestations and overlap with other autoimmune conditions. Large Language Models (LLMs) are currently regarded as having the potential to assist clinicians in expediting decision‐making. This study aimed to evaluate the performance of four LLMs in differentiating SLE from clinically mimicking conditions.
Methods
A retrospective diagnostic accuracy study was conducted involving 100 patients at a rheumatology center: 50 patients with confirmed SLE and 50 non‐SLE patients with conditions including rheumatoid arthritis, systemic sclerosis, axial spondyloarthritis, psoriatic arthritis, myositis, ANCA‐associated vasculitis, mixed connective tissue disease, undifferentiated connective tissue disease, and fibromyalgia. Four LLMs were evaluated: Deepseek, ChatGPT 4.0, Claude Sonnet 4, and Gemini. The 2019 European Alliance of Associations for Rheumatology/American College of Rheumatology (EULAR/ACR) classification criteria were applied. Diagnostic accuracy, positive predictive value (PPV), negative predictive value (NPV), and Area Under the Receiver Operating Characteristic Curve (AUC) were calculated. IBM SPSS Statistics version 25 was used for all analyses.
Results
Gemini achieved the highest performance score, with an accuracy of 96% (95% CI: 91.2–100.0%), sensitivity of 94% (95% CI: 89.3–98.7%), specificity of 98% (95% CI: 93.1–100.0%), and an AUC of 0.960. ChatGPT 4.0 and Claude Sonnet 4 exhibited comparable accuracy. Deepseek recorded the lowest performance score.
Conclusion
Gemini demonstrated significant potential to assist clinicians in differentiating SLE from mimicking conditions. Nevertheless, prospective validation in real‐world clinical settings is required before these tools can be reliably integrated into clinical practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Rheumatology Division, Internal Medicine Department, Dr Saiful General Hospital, Brawijaya University, Malang, Indonesia.
ORCID-Profile: Mirza Zaka Pratama, Bagus Putu Putra Suryana, Cesarius Singgih Wahono, Rina Kurnia Putri
Zitieren
APA
Pratama, M. Z., Suryana, B. P. P., Wahono, C. S., & Putri, R. K. (2026). Performance of Large Language Models in Differentiating Systemic Lupus Erythematosus From Mimicking Conditions Using the 2019 EULAR / ACR Criteria: A Comparative Analysis. International Journal of Rheumatic Diseases, 29(5). https://doi.org/10.1111/1756-185x.70713
Vancouver
Pratama MZ, Suryana BPP, Wahono CS, Putri RK. Performance of Large Language Models in Differentiating Systemic Lupus Erythematosus From Mimicking Conditions Using the 2019 EULAR / ACR Criteria: A Comparative Analysis. International Journal of Rheumatic Diseases. 2026;29(5). doi:10.1111/1756-185x.70713
BibTeX
@article{Pratama2026,
author = {Pratama, Mirza Zaka and Suryana, Bagus Putu Putra and Wahono, Cesarius Singgih and Putri, Rina Kurnia},
title = {Performance of Large Language Models in Differentiating Systemic Lupus Erythematosus From Mimicking Conditions Using the 2019 EULAR / ACR Criteria: A Comparative Analysis},
journal = {International Journal of Rheumatic Diseases},
year = {2026},
volume = {29},
number = {5},
doi = {10.1111/1756-185x.70713}
}
EUVIMED