Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis
Diagnostische Leistung von Machine Learning bei systemischem Lupus erythematodes: systematische Übersichtsarbeit und Metaanalyse
Journal of Medical Internet Research · 2026-09-04 · 28 · e90209-e90209
DOI: 10.2196/90209 ↗Auf einen Blick
ML-Modelle zeigten für 3 SLE-bezogene Aufgaben eine hohe diagnostische Genauigkeit. Die Aussagekraft ist jedoch durch breite Prädiktionsintervalle und Bias-Risiko eingeschränkt.
Fragestellung
Wie gut sind ML- und DL-Modelle für die Diagnose bzw. Klassifikation von SLE, Lupusnephritis und neuropsychiatrischem SLE?
Methode
Systematische Übersichtsarbeit und Metaanalyse diagnostischer Studien; Suche in PubMed, Embase, Cochrane Library, Web of Science und IEEE Xplore von Januar 2014 bis April 2026; Bewertung mit QUADAS-AI und GRADE.
Ergebnisse
29 Studien: 17 zu SLE-Klassifikation, 5 zu Lupusnephritis und 7 zu NPSLE. Gepoolte Sensitivität 0,91 (95 %-KI 0,86-0,94; 95 % PI 0,56-0,99), Spezifität 0,94 (95 %-KI 0,91-0,96; 95 % PI 0,69-0,99).
Einschränkungen
Alle Studien waren retrospektiv; nur 9 von 29 führten eine unabhängige externe Validierung durch. In 22 von 29 war das Verzerrungsrisiko hoch oder unklar; keine Studie berichtete Kalibrierung oder net clinical benefit.
Schlussfolgerung der Autor:innen
ML-Modelle zeigten eine vielversprechende diagnostische Genauigkeit, aber breite Prädiktionsintervalle, begrenzte externe Validierung und hohes Bias-Risiko schränken die Aussagekraft zur Anwendbarkeit in der Praxis ein.
Kernaussagen
- 29 Studien zu 3 SLE-bezogenen diagnostischen Aufgaben
- Pooled sensitivity 0,91; pooled specificity 0,94
- Nur 9 von 29 mit externer Validierung; Bias häufig hoch oder unklar
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
At a glance
Metaanalyse in Journal of Medical Internet Research, published online on 2026-09-04. Written by Bingduo Wang and 3 co-authors. Institution: Department of Anesthesiology and Intensive Care, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China. Major MEDLINE topics: Lupus Erythematosus, Systemic, Machine Learning, Diagnosis, Computer-Assisted. 78 references. The full text is freely available in PubMed Central.
Abstract (original language)
Background
Early and accurate diagnosis of systemic lupus erythematosus (SLE) and its organ involvement is essential. Previous reviews of machine learning (ML) in SLE combined heterogeneous tasks and validation strategies and may have overinterpreted model performance.
Objective
This study evaluated the diagnostic performance of ML and deep learning (DL) models for 3 clinically distinct SLE-related tasks: SLE classification or diagnosis, lupus nephritis (LN) diagnosis, and neuropsychiatric systemic lupus erythematosus (NPSLE) discrimination. We also assessed methodological quality and certainty of evidence.
Methods
PubMed, Embase, Cochrane Library, Web of Science, and IEEE Xplore were searched from January 2014 to April 2026. Eligible peer-reviewed diagnostic accuracy studies developed or validated ML or DL models for 1 of the 3 prespecified tasks, used an accepted reference standard, and provided data for a 2×2 contingency table. Bivariate random-effects meta-analyses with the Hartung-Knapp-Sidik-Jonkman adjustment were used to pool sensitivity and specificity. We reported 95% prediction intervals (PIs), assessed risk of bias using the Quality Assessment of Diagnostic Accuracy Studies for Artificial Intelligence tool (QUADAS-AI; Viknesh Sounderajah [Imperial College London]), and evaluated certainty of evidence using the Grading of Recommendations Assessment, Development, and Evaluation framework for diagnostic test accuracy.
Results
Twenty-nine studies were included: 17 for SLE classification, 5 for LN diagnosis, and 7 for NPSLE discrimination. In the primary task-stratified analysis, pooled sensitivity was 0.91 (95% CI 0.86-0.94; 95% PI 0.56-0.99), and pooled specificity was 0.94 (95% CI 0.91-0.96; 95% PI 0.69-0.99), with low heterogeneity ( I ²=23.9% and 22.9%, respectively). DL models showed a sensitivity of 0.93 and specificity of 0.95, compared with 0.88 and 0.94 for traditional ML models. Certainty of evidence was high for most analyses but low for LN diagnosis because of inconsistency and imprecision. All studies were retrospective, and only 9 of 29 (31%) performed independent external validation. Overall risk of bias was high or unclear in 22 of 29 (75.9%) studies. No study reported model calibration, decision-curve analysis, or net clinical benefit.
Conclusions
ML models showed promising diagnostic accuracy across 3 distinct SLE-related tasks, but wide PIs, limited external validation, and pervasive risk of bias restrict conclusions about real-world generalizability. Prospective multicenter studies with standardized tasks and reference standards, independent external validation, and formal assessment of calibration and clinical utility are required before clinical implementation.
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Department of Anesthesiology and Intensive Care, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, China.
- Department of Epidemiology and Statistics, Institute of Basic Medical Sciences Chinese Academy of Medical Sciences, School of Basic Medicine Peking Union Medical College, Beijing, China.
- Department of Proctology, The First Affiliated Hospital of Xinjiang Medical University, Xinjiang, China.
- Department of Hematology, The First Affiliated Hospital of Zhengzhou University, No. 1, Jianshe East Road, Erqi District, Zhengzhou, China, 86 15067607819.
Cite
APA
Wang, B., Wang, Z., Liu, Y., & Ge, F. (2026). Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis. Journal of Medical Internet Research, 28, e90209-e90209. https://doi.org/10.2196/90209
Vancouver
Wang B, Wang Z, Liu Y, Ge F. Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis. Journal of Medical Internet Research. 2026;28:e90209-e90209. doi:10.2196/90209
BibTeX
@article{Wang2026,
author = {Wang, Bingduo and Wang, Zichao and Liu, Yang and Ge, Fangfang},
title = {Diagnostic Performance of Machine Learning for Systemic Lupus Erythematosus: Systematic Review and Meta-Analysis},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e90209--e90209},
doi = {10.2196/90209}
}
EUVIMED