Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis.

J Med Internet ResSep 4, 2026 (epub)
Clinical ResearchRheumatologyOpen access

Bingduo Wang, Zichao Wang, Yang Liu et al.

✦ AI-curated · Sources linked

In 30 seconds

This systematic review and meta-analysis evaluated the diagnostic performance of machine learning (ML) and deep learning (DL) models for systemic lupus erythematosus (SLE) classification, lupus nephritis (LN) diagnosis, and neuropsychiatric SLE discrimination. The analysis included 29 studies, revealing a pooled sensitivity of 0.91 and specificity of 0.94 for SLE classification. The study highlights the need for improved validation and methodological rigor in future research.

Key findings

  • Pooled sensitivity for SLE classification was 0.91 (95% CI 0.86-0.94).
  • Pooled specificity for SLE classification was 0.94 (95% CI 0.91-0.96).
  • Deep learning models demonstrated a sensitivity of 0.93 and specificity of 0.95.
  • Only 31% of studies performed independent external validation.

Why it matters

Accurate and early diagnosis of systemic lupus erythematosus is crucial for effective management. Understanding the performance of ML and DL models can inform future diagnostic strategies, although current limitations must be addressed.

What to keep in mind

All included studies were retrospective, and 75.9% had high or unclear risk of bias.

Source

Published in J Med Internet Res. This summary was written by xxcode from the publication's abstract and metadata. It is not peer reviewed and is not a substitute for the original article. For clinical decisions, review the original publication.

ShareTelegramLinkedIn

AI-generated summaries may contain errors or omissions. Verify clinically important information with the original publication.

More in Rheumatology

Want this personalized?

Stop searching the literature. Choose what you follow and xxcode will build your personalized medical digest.

  • Your specialties
  • Your filters and thresholds
  • Clinical Research + Case Reports, tuned separately
  • Automatic weekly delivery
  • Audio and text

Prefer listening? Personalized audio digests are available with Pro.

Stay updated for free

Get the 3 most interesting publications in one specialty each week.

Weekly email. Unsubscribe anytime.